Search results for: BrasTS dataset

Authors: Jui-Chien Hsieh

Abstract:

Background:12-lead electrocardiography(ECG) is one of frequently-used tools to detect atrial fibrillation (AF), which might degenerate into life-threaten stroke, in clinical Practice. Based on this study, the AF detection by the clinically-used 12-lead ECG device has only 0.73~0.77 positive predictive value (ppv). Objective: It is on great demand to develop a new algorithm to improve the precision of AF detection using 12-lead ECG. Due to the progress on artificial intelligence (AI), we develop an ECG deep model that has the ability to recognize AF patterns and reduce false-positive errors. Methods: In this study, (1) 570-sample 12-lead ECG reports whose computer interpretation by the ECG device was AF were collected as the training dataset. The ECG reports were interpreted by 2 senior cardiologists, and confirmed that the precision of AF detection by the ECG device is 0.73.; (2) 88 12-lead ECG reports whose computer interpretation generated by the ECG device was AF were used as test dataset. Cardiologist confirmed that 68 cases of 88 reports were AF, and others were not AF. The precision of AF detection by ECG device is about 0.77; (3) A parallel 4-layer 1 dimensional convolutional neural network (CNN) was developed to identify AF based on limb-lead ECGs and chest-lead ECGs. Results: The results indicated that this model has better performance on AF detection than traditional computer interpretation of the ECG device in 88 test samples with 0.94 ppv, 0.98 sensitivity, 0.80 specificity. Conclusions: As compared to the clinical ECG device, this AI ECG model promotes the precision of AF detection from 0.77 to 0.94, and can generate impacts on clinical applications.

Keywords: 12-lead ECG, atrial fibrillation, deep learning, convolutional neural network

Procedia PDF Downloads 89

Authors: Nahla H. Alaswadko, Rayya A. Hassan, Bayar N. Mohammed

Abstract:

Empirical deterministic models have been developed to predict roughness progression of heavy duty spray sealed pavements for a dataset representing rural arterial roads. The dataset provides a good representation of the relevant network and covers a wide range of operating and environmental conditions. A sample with a large size of historical time series data for many pavement sections has been collected and prepared for use in multilevel regression analysis. The modelling parameters include road roughness as performance parameter and traffic loading, time, initial pavement strength, reactivity level of subgrade soil, climate condition, and condition of drainage system as predictor parameters. The purpose of this paper is to report the approaches adopted for models development and validation. The study presents multilevel models that can account for the correlation among time series data of the same section and to capture the effect of unobserved variables. Study results show that the models fit the data very well. The contribution and significance of relevant influencing factors in predicting roughness progression are presented and explained. The paper concludes that the analysis approach used for developing the models confirmed their accuracy and reliability by well-fitting to the validation data.

Keywords: roughness progression, empirical model, pavement performance, heavy duty pavement

Procedia PDF Downloads 135

Authors: Sagri Sharma

Abstract:

Analysis of diseases integrating multi-factors increases the complexity of the problem and therefore, development of frameworks for the analysis of diseases is an issue that is currently a topic of intense research. Due to the inter-dependence of the various parameters, the use of traditional methodologies has not been very effective. Consequently, newer methodologies are being sought to deal with the problem. Supervised Learning Algorithms are commonly used for performing the prediction on previously unseen data. These algorithms are commonly used for applications in fields ranging from image analysis to protein structure and function prediction and they get trained using a known dataset to come up with a predictor model that generates reasonable predictions for the response to new data. Gene expression profiles generated by DNA analysis experiments can be quite complex since these experiments can involve hypotheses involving entire genomes. The application of well-known machine learning algorithm - Support Vector Machine - to analyze the expression levels of thousands of genes simultaneously in a timely, automated and cost effective way is thus used. The objectives to undertake the presented work are development of a methodology to identify genes relevant to Hepatocellular Carcinoma (HCC) from gene expression dataset utilizing supervised learning algorithms and statistical evaluations along with development of a predictive framework that can perform classification tasks on new, unseen data.

Keywords: artificial intelligence, biomarker, gene expression datasets, hepatocellular carcinoma, machine learning, supervised learning algorithms, support vector machine

Procedia PDF Downloads 401

Authors: E. M. D. Akuoko, Eliana Vasquez Osorio, Marcel Van Herk, Marianne Aznar

Abstract:

Radiotherapy is an integral part of treatment for many patients with breast cancer. However, side effects can occur, e.g., fibrosis or erythema. If patients at higher risks of radiation-induced side effects could be identified before treatment, they could be given more individual information about the risks and benefits of radiotherapy. We hypothesize that breast density is correlated with the risk of side effects and present a novel method for automatic evaluation based on radiotherapy planning CT scans. Methods: 799 supine CT scans of breast radiotherapy patients were available from the REQUITE dataset. The methodology was first established in a subset of 114 patients (cohort 1) before being applied to the whole dataset (cohort 2). All patients were scanned in the supine position, with arms up, and the treated breast (ipsilateral) was identified. Manual experts contour available in 96 patients for both the ipsilateral and contralateral breast in cohort 1. Breast tissue was segmented using atlas-based automatic contouring software, ADMIRE® v3.4 (Elekta AB, Sweden). Once validated, the automatic segmentation method was applied to cohort 2. Breast density was then investigated by thresholding voxels within the contours, using Otsu threshold and pixel intensity ranges based on Hounsfield units (-200 to -100 for fatty tissue, and -99 to +100 for fibro-glandular tissue). Volumetric breast density (VBD) was defined as the volume of fibro-glandular tissue / (volume of fibro-glandular tissue + volume of fatty tissue). A sensitivity analysis was performed to verify whether calculated VBD was affected by the choice of breast contour. In addition, we investigated the correlation between volumetric breast density (VBD) and patient age and breast size. VBD values were compared between ipsilateral and contralateral breast contours. Results: Estimated VBD values were 0.40 (range 0.17-0.91) in cohort 1, and 0.43 (0.096-0.99) in cohort 2. We observed ipsilateral breasts to be denser than contralateral breasts. Breast density was negatively associated with breast volume (Spearman: R=-0.5, p-value < 2.2e-16) and age (Spearman: R=-0.24, p-value = 4.6e-10). Conclusion: VBD estimates could be obtained automatically on a large CT dataset. Patients’ age or breast volume may not be the only variables that explain breast density. Future work will focus on assessing the usefulness of VBD as a predictive variable for radiation-induced side effects.

Keywords: breast cancer, automatic image segmentation, radiotherapy, big data, breast density, medical imaging

Procedia PDF Downloads 107

Authors: Toktam Khatibi

Abstract:

Self-supervised learning (SSL) includes machine learning models that are trained on one aspect and/or one part of the input to learn other aspects and/or part of it. SSL models are divided into two different categories, including pre-text task-based models and contrastive learning ones. Pre-text tasks are some auxiliary tasks learning pseudo-labels, and the trained models are further fine-tuned for downstream tasks. However, one important disadvantage of SSL using pre-text task solving is defining an appropriate pre-text task for each image dataset with a variety of image modalities. Therefore, it is required to design an appropriate pretext task automatically for each dataset and each downstream task. To the best of our knowledge, the automatic designing of pretext tasks for image analysis has not been considered yet. In this paper, we present a framework based on In-context learning that describes each task based on its input and output data using a pre-trained image transformer. Our proposed method combines the input image and its learned description for optimizing the pre-text task design and its hyper-parameters using Meta-learning models. The representations learned from the pre-text tasks are fine-tuned for solving the downstream tasks. We demonstrate that our proposed framework outperforms the compared ones on unseen tasks and image modalities in addition to its superior performance for previously known tasks and datasets.

Keywords: in-context learning (ICL), meta learning, self-supervised learning (SSL), vision-language domain, transformers

Procedia PDF Downloads 45

Authors: Zakaria Kharbouch, Mustapha Bouchaara, F. Elkouihen, A. Habbal, A. Ratnani, A. Faik

Abstract:

Solid-state lithium-ion batteries have garnered increasing interest in modern energy research due to their potential for safer, more efficient, and sustainable energy storage systems. Among the critical components of these batteries, the electrolyte plays a pivotal role, with LLZO garnet-based electrolytes showing significant promise. Garnet materials offer intrinsic advantages such as high Li-ion conductivity, wide electrochemical stability, and excellent compatibility with lithium metal anodes. However, optimizing ionic conductivity in garnet structures poses a complex challenge, primarily due to the multitude of potential dopants that can be incorporated into the LLZO crystal lattice. The complexity of material design, influenced by numerous dopant options, requires a systematic method to find the most effective combinations. This study highlights the utility of machine learning (ML) techniques in the materials discovery process to navigate the complex range of factors in garnet-based electrolytes. Collaborators from the materials science and ML fields worked with a comprehensive dataset previously employed in a similar study and collected from various literature sources. This dataset served as the foundation for an extensive data refinement phase, where meticulous error identification, correction, outlier removal, and garnet-specific feature engineering were conducted. This rigorous process substantially improved the dataset's quality, ensuring it accurately captured the underlying physical and chemical principles governing garnet ionic conductivity. The data refinement effort resulted in a significant improvement in the predictive performance of the machine learning model. Originally starting at an accuracy of 0.32, the model underwent substantial refinement, ultimately achieving an accuracy of 0.88. This enhancement highlights the effectiveness of the interdisciplinary approach and underscores the substantial potential of machine learning techniques in materials science research.

Keywords: lithium batteries, all-solid-state batteries, machine learning, solid state electrolytes

Procedia PDF Downloads 25

Authors: Hankyu Lee, Seoung Bum Kim

Abstract:

The issue with imbalance and overlapping in the class distribution becomes important in various applications of data mining. The imbalanced dataset is a special case in classification problems in which the number of observations of one class (i.e., major class) heavily exceeds the number of observations of the other class (i.e., minor class). Overlapped dataset is the case where many observations are shared together between the two classes. Imbalanced and overlapped data can be frequently found in many real examples including fraud and abuse patients in healthcare, quality prediction in manufacturing, text classification, oil spill detection, remote sensing, and so on. The class imbalance and overlap problem is the challenging issue because this situation degrades the performance of most of the standard classification algorithms. In this study, we propose a classification procedure that can effectively handle imbalanced and overlapped datasets by splitting data space into three parts: nonoverlapping, light overlapping, and severe overlapping and applying the classification algorithm in each part. These three parts were determined based on the Hausdorff distance and the margin of the modified support vector machine. An experiments study was conducted to examine the properties of the proposed method and compared it with other classification algorithms. The results showed that the proposed method outperformed the competitors under various imbalanced and overlapped situations. Moreover, the applicability of the proposed method was demonstrated through the experiment with real data.

Keywords: classification, imbalanced data with class overlap, split data space, support vector machine

Procedia PDF Downloads 276

Authors: Umm-E-Hani, Faiza Babar, Hanif Durad

Abstract:

Malware-detecting approaches suffer many limitations, due to which all anti-malware solutions have failed to be reliable enough for detecting zero-day malware. Signature-based solutions depend upon the signatures that can be generated only when malware surfaces at least once in the cyber world. Another approach that works by detecting the anomalies caused in the environment can easily be defeated by diligently and intelligently written malware. Solutions that have been trained to observe the behavior for detecting malicious files have failed to cater to the malware capable of detecting the sandboxed or protected environment. Machine learning and deep learning-based approaches greatly suffer in training their models with either an imbalanced dataset or an inadequate number of samples. AI-based anti-malware solutions that have been trained with enough samples targeted a selected feature vector, thus ignoring the input of leftover features in the maliciousness of malware just to cope with the lack of underlying hardware processing power. Our research focuses on producing an anti-malware solution for detecting malicious PE files by circumventing the earlier-mentioned shortcomings. Our proposed framework, which is based on automated feature engineering through autoencoders, trains the model over a fairly large dataset. It focuses on the visual patterns of malware samples to automatically extract the meaningful part of the visual pattern. Our experiment has successfully produced a state-of-the-art accuracy of 99.54 % over test data.

Keywords: malware, auto encoders, automated feature engineering, classification

Procedia PDF Downloads 46

Authors: Ki-Yeo Kim

Abstract:

Trends in genetics are transforming in order to identify differential coexpressions of correlated gene expression rather than the significant individual gene. Moreover, it is known that a combined biomarker pattern improves the discrimination of a specific cancer. The identification of the combined biomarker is also necessary for the early detection of invasive oral squamous cell carcinoma (OSCC). To identify the combined biomarker that could improve the discrimination of OSCC, we explored an appropriate number of genes in a combined gene set in order to attain the highest level of accuracy. After detecting a significant gene set, including the pre-defined number of genes, a combined expression was identified using the weights of genes in a gene set. We used the Principal Component Analysis (PCA) for the weight calculation. In this process, we used three public microarray datasets. One dataset was used for identifying the combined biomarker, and the other two datasets were used for validation. The discrimination accuracy was measured by the out-of-bag (OOB) error. There was no relation between the significance and the discrimination accuracy in each individual gene. The identified gene set included both significant and insignificant genes. One of the most significant gene sets in the classification of normal and OSCC included MMP1, SOCS3 and ACOX1. Furthermore, in the case of oral dysplasia and OSCC discrimination, two combined biomarkers were identified. The combined genomic expression achieved better performance in the discrimination of different conditions than in a single significant gene. Therefore, it could be expected that accurate diagnosis for cancer could be possible with a combined biomarker.

Keywords: oral squamous cell carcinoma, combined biomarker, microarray dataset, correlated genes

Procedia PDF Downloads 392

Authors: Krishna Mohan Bathula, Fatou Bintou Loucoubar, FNU Kaleemunnisa, Christelle Scharff, Mark Anthony De Castro

Abstract:

Voice recognition algorithms such as automatic speech recognition and text-to-speech systems with African languages can play an important role in bridging the digital divide of Artificial Intelligence in Africa, contributing to the establishment of a fully inclusive information society. This paper proposes a Deep Learning model that can classify the user responses as inputs for an interactive voice response system. A dataset with Wolof language words ‘yes’ and ‘no’ is collected as audio recordings. A two stage Data Augmentation approach is adopted for enhancing the dataset size required by the deep neural network. Data preprocessing and feature engineering with Mel-Frequency Cepstral Coefficients are implemented. Convolutional Neural Networks (CNNs) have proven to be very powerful in image classification and are promising for audio processing when sounds are transformed into spectra. For performing voice response classification, the recordings are transformed into sound frequency feature spectra and then applied image classification methodology using a deep CNN model. The inference model of this trained and reusable Wolof voice response recognition system can be integrated with many applications associated with both web and mobile platforms.

Keywords: automatic speech recognition, interactive voice response, voice response recognition, wolof word classification

Procedia PDF Downloads 85

Authors: Antonia Stanojević, Agnes Akkerman

Abstract:

In contemporary society, economically active people typically spend most of their waking hours doing their job. Having that in mind, this research examines how socialization at the workplace shapes political preferences. Innovatively, it examines, in particular, the possible relationship between employees’ voice suppression by the employer and the formation of their political preferences. Since the employer is perceived as an authority figure, their behavior might induce spillovers to attitudes about political authorities and authoritarian governance. Therefore, a positive effect of suppression of voice by employers on employees' preference for authoritarian governance is expected. Furthermore, this relation is expected to be mediated by two mechanisms: system justification and power distance. Namely, it is expected that suppression of voice would create a power distance organizational climate and increase employees’ acceptance of unequal distribution of power, as well as evoke attempts of oppression rationalization through system justification. The hypotheses will be tested on the data gathered within the first wave of Work and Politics Dataset 2017 (N=6000), which allows for a wide range of demographic and psychological control variables. Although a cross-sectional analysis to be used at this point does not allow for causal inferences, the confirmation of expected relationships would encourage and justify further longitudinal research on the same panel dataset, in order to get a clearer image of the causal relationship between employers' suppression of voice and workers' political preferences.

Keywords: authoritarian values, political preferences, power distance, system justification, voice suppression

Procedia PDF Downloads 240

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: artificial neural networks, breast cancer, classifiers, cervical cancer, f-score, machine learning, precision, recall

Procedia PDF Downloads 248

Authors: Yeliz Karaca, Carlo Cattani

Abstract:

This study focuses on the local Holder exponent as a measure of the function regularity for time series related to finance data. In this study, the attributes of the finance dataset belonging to 13 countries (India, China, Japan, Sweden, France, Germany, Italy, Australia, Mexico, United Kingdom, Argentina, Brazil, USA) located in 5 different continents (Asia, Europe, Australia, North America and South America) have been examined.These countries are the ones mostly affected by the attributes with regard to financial development, covering a period from 2012 to 2017. Our study is concerned with the most important attributes that have impact on the development of finance for the countries identified. Our method is comprised of the following stages: (a) among the multi fractal methods and Brownian motion Holder regularity functions (polynomial, exponential), significant and self-similar attributes have been identified (b) The significant and self-similar attributes have been applied to the Artificial Neuronal Network (ANN) algorithms (Feed Forward Back Propagation (FFBP) and Cascade Forward Back Propagation (CFBP)) (c) the outcomes of classification accuracy have been compared concerning the attributes that have impact on the attributes which affect the countries’ financial development. This study has enabled to reveal, through the application of ANN algorithms, how the most significant attributes are identified within the relevant dataset via the Holder functions (polynomial and exponential function).

Keywords: artificial neural networks, finance data, Holder regularity, multifractals

Procedia PDF Downloads 220

Authors: Jonathan Gong

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deep learning, image processing, machine learning

Procedia PDF Downloads 96

Authors: U. Borasi, Amit Kr. Jain, Rakesh, Piyush Jain

Abstract:

Data collection, data preparation, model training, model evaluation, and deployment are all processes in a typical machine learning workflow. Training data needs to be gathered and organised. This often entails collecting a sizable dataset and cleaning it to remove or correct any inaccurate or missing information. Preparing the data for use in the machine learning model requires pre-processing it after it has been acquired. This often entails actions like scaling or normalising the data, handling outliers, selecting appropriate features, reducing dimensionality, etc. This pre-processed data is then used to train a model on some machine learning algorithm. After the model has been trained, it needs to be assessed by determining metrics like accuracy, precision, and recall, utilising a test dataset. Every time a new model is built, both data pre-processing and model training—two crucial processes in the Machine learning (ML) workflow—must be carried out. Thus, there are various Machine Learning algorithms that can be employed for every single approach to data pre-processing, generating a large set of combinations to choose from. Example: for every method to handle missing values (dropping records, replacing with mean, etc.), for every scaling technique, and for every combination of features selected, a different algorithm can be used. As a result, in order to get the optimum outcomes, these tasks are frequently repeated in different combinations. This paper suggests a simple architecture for organizing this largely produced “combination set of pre-processing steps and algorithms” into an automated workflow which simplifies the task of carrying out all possibilities.

Keywords: machine learning, automation, AUTOML, architecture, operator pool, configuration, scheduler

Procedia PDF Downloads 26

Authors: Kemka Ihemelandu, Chukwuemeka Ihemelandu

Abstract:

Melanoma remains a public health crisis, with incidence rates increasing rapidly in the past decades. Improving diagnostic accuracy to decrease misdiagnosis using Artificial intelligence (AI) continues to be documented. Unfortunately, unintended racially biased outcomes, a product of lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone, have increasingly been recognized as a problem.Resulting in noted limitations of the accuracy of the Convolutional neural network (CNN)models. CNN models are prone to biased output due to biases in the dataset used to train them. Our aim in this study was the optimization of convolutional neural network algorithms to mitigate bias in the automated diagnosis of melanoma. We hypothesized that our proposed training algorithms based on a data augmentation method to optimize the diagnostic accuracy of a CNN classifier by generating new training samples from the original ones will reduce bias in the automated diagnosis of melanoma. We applied geometric transformation, including; rotations, translations, scale change, flipping, and shearing. Resulting in a CNN model that provided a modifiedinput data making for a model that could learn subtle racial features. Optimal selection of the momentum and batch hyperparameter increased our model accuracy. We show that our augmented model reduces bias while maintaining accuracy in the automated diagnosis of melanoma.

Keywords: bias, augmentation, melanoma, convolutional neural network

Procedia PDF Downloads 175

Authors: Mace Bentley, Zhuojun Duan, Tobias Gerken, Dudley Bonsal, Henry Way, Endre Szakal, Mia Pham, Hunter Donaldson, Chelsea Lang, Hayden Abbott, Leah Wilcynzski

Abstract:

Air pollution has the potential to modify the lifespan and intensity of thunderstorms and the properties of lightning. Using data mining and geovisualization, we investigate how background climate and weather conditions shape variability in urban air pollution and how this, in turn, shapes thunderstorms as measured by the intensity, distribution, and frequency of cloud-to-ground lightning. A spatiotemporal analysis was conducted in order to identify thunderstorms using high-resolution lightning detection network data. Over seven million lightning flashes were used to identify more than 196,000 thunderstorms that occurred between 2006 - 2020 in the Washington, DC Metropolitan Region. Each lightning flash in the dataset was grouped into thunderstorm events by means of a temporal and spatial clustering algorithm. Once the thunderstorm event database was constructed, hourly wind direction, wind speed, and atmospheric thermodynamic data were added to the initiation and dissipation times and locations for the 196,000 identified thunderstorms. Hourly aerosol and air quality data for the thunderstorm initiation times and locations were also incorporated into the dataset. Developing thunderstorm climatologies using a lightning tracking algorithm and lightning detection network data was found to be useful for visualizing the spatial and temporal distribution of urban augmented thunderstorms in the region.

Keywords: lightning, urbanization, thunderstorms, climatology

Procedia PDF Downloads 48

Authors: Dmitriy Babenko, Sergey Yegorov, Ilya Korshukov, Aidana Sultanbekova, Valentina Barkhanskaya, Tatiana Bashirova, Yerzhan Zhunusov, Yevgeniya Li, Viktoriya Parakhina, Svetlana Kolesnichenko, Yeldar Baiken, Aruzhan Pralieva, Zhibek Zhumadilova, Matthew S. Miller, Gonzalo H. Hortelano, Anar Turmuhambetova, Antonella E. Chesca, Irina Kadyrova

Abstract:

Introduction: The rapidly evolving COVID-19 pandemic, along with the re-emergence of pathogens causing acute respiratory infections (ARI), has necessitated the development of novel diagnostic tools to differentiate various causes of ARI. MALDI-MS, due to its wide usage and affordability, has been proposed as a potential instrument for diagnosing SARS-CoV-2 versus non-SARS-CoV-2 ARI. The aim of this study was to investigate the potential of MALDI-MS in conjunction with a machine learning model to accurately distinguish between symptomatic infections caused by SARS-CoV-2 and non-SARS-CoV-2 during both the early and later phases of the pandemic. Furthermore, this study aimed to analyze mass spectrometry (MS) data obtained from nasal swabs of healthy individuals. Methods: We gathered mass spectra from 252 samples, comprising 108 SARS-CoV-2-positive samples obtained in 2020 (Covid 2020), 7 SARS-CoV- 2-positive samples obtained in 2023 (Covid 2023), 71 samples from symptomatic individuals without SARS-CoV-2 (Control non-Covid ARVI), and 66 samples from healthy individuals (Control healthy). All the samples were subjected to RT-PCR testing. For data analysis, we employed the caret R package to train and test seven machine-learning algorithms: C5.0, KNN, NB, RF, SVM-L, SVM-R, and XGBoost. We conducted a training process using a five-fold (outer) nested repeated (five times) ten-fold (inner) cross-validation with a randomized stratified splitting approach. Results: In this study, we utilized the Covid 2020 dataset as a case group and the non-Covid ARVI dataset as a control group to train and test various machine learning (ML) models. Among these models, XGBoost and SVM-R demonstrated the highest performance, with accuracy values of 0.97 [0.93, 0.97] and 0.95 [0.95; 0.97], specificity values of 0.86 [0.71; 0.93] and 0.86 [0.79; 0.87], and sensitivity values of 0.984 [0.984; 1.000] and 1.000 [0.968; 1.000], respectively. When examining the Covid 2023 dataset, the Naive Bayes model achieved the highest classification accuracy of 43%, while XGBoost and SVM-R achieved accuracies of 14%. For the healthy control dataset, the accuracy of the models ranged from 0.27 [0.24; 0.32] for k-nearest neighbors to 0.44 [0.41; 0.45] for the Support Vector Machine with a radial basis function kernel. Conclusion: Therefore, ML models trained on MALDI MS of nasopharyngeal swabs obtained from patients with Covid during the initial phase of the pandemic, as well as symptomatic non-Covid individuals, showed excellent classification performance, which aligns with the results of previous studies. However, when applied to swabs from healthy individuals and a limited sample of patients with Covid in the late phase of the pandemic, ML models exhibited lower classification accuracy.

Keywords: SARS-CoV-2, MALDI-TOF MS, ML models, nasopharyngeal swabs, classification

Procedia PDF Downloads 72

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

Abstract:

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

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

Procedia PDF Downloads 70

Authors: Hany Elsaid Fawaz Abdallah

Abstract:

This study presents a new artificial neural network(ANN) model to predict the Nusselt Number and pressure drop for the turbulent flow in a triangular corrugated plate heat exchanger for forced air and turbulent water flow. An experimental investigation was performed to create a new dataset for the Nusselt Number and pressure drop values in the following range of dimensionless parameters: The plate corrugation angles (from 0° to 60°), the Reynolds number (from 10000 to 40000), pitch to height ratio (from 1 to 4), and Prandtl number (from 0.7 to 200). Based on the ANN performance graph, the three-layer structure with {12-8-6} hidden neurons has been chosen. The training procedure includes back-propagation with the biases and weight adjustment, the evaluation of the loss function for the training and validation dataset and feed-forward propagation of the input parameters. The linear function was used at the output layer as the activation function, while for the hidden layers, the rectified linear unit activation function was utilized. In order to accelerate the ANN training, the loss function minimization may be achieved by the adaptive moment estimation algorithm (ADAM). The ‘‘MinMax’’ normalization approach was utilized to avoid the increase in the training time due to drastic differences in the loss function gradients with respect to the values of weights. Since the test dataset is not being used for the ANN training, a cross-validation technique is applied to the ANN network using the new data. Such procedure was repeated until loss function convergence was achieved or for 4000 epochs with a batch size of 200 points. The program code was written in Python 3.0 using open-source ANN libraries such as Scikit learn, TensorFlow and Keras libraries. The mean average percent error values of 9.4% for the Nusselt number and 8.2% for pressure drop for the ANN model have been achieved. Therefore, higher accuracy compared to the generalized correlations was achieved. The performance validation of the obtained model was based on a comparison of predicted data with the experimental results yielding excellent accuracy.

Keywords: artificial neural networks, corrugated channel, heat transfer enhancement, Nusselt number, pressure drop, generalized correlations

Procedia PDF Downloads 52

Authors: Jianghao Hu, Hongyu Wang

Abstract:

The effective and efficient human pose estimation algorithm is an important task for real-time human pose estimation on mobile devices. This paper proposes a light-weight human key points detection algorithm, Light-Weight Network for Real-Time Pose Estimation (LWPE). LWPE uses light-weight backbone network and depthwise separable convolutions to reduce parameters and lower latency. LWPE uses the feature pyramid network (FPN) to fuse the high-resolution, semantically weak features with the low-resolution, semantically strong features. In the meantime, with multi-scale prediction, the predicted result by the low-resolution feature map is stacked to the adjacent higher-resolution feature map to intermediately monitor the network and continuously refine the results. At the last step, the key point coordinates predicted in the highest-resolution are used as the final output of the network. For the key-points that are difficult to predict, LWPE adopts the online hard key points mining strategy to focus on the key points that hard predicting. The proposed algorithm achieves excellent performance in the single-person dataset selected in the AI (artificial intelligence) challenge dataset. The algorithm maintains high-precision performance even though the model only contains 3.9M parameters, and it can run at 225 frames per second (FPS) on the generic graphics processing unit (GPU).

Keywords: depthwise separable convolutions, feature pyramid network, human pose estimation, light-weight backbone

Procedia PDF Downloads 122

Authors: Chris Schoborg, Morgan C. Wang

Abstract:

In the realm of the National Football League (NFL), substantial dedication of time and effort is invested by both players and coaches in meticulously analyzing the game footage of their opponents. The primary aim is to anticipate the actions of the opposing team. Defensive players and coaches are especially focused on deciphering their adversaries' intentions to effectively counter their strategies. Acquiring insights into the specific play type and its intended direction on the field would confer a significant competitive advantage. This study establishes pre-snap information as the cornerstone for predicting both the play type (e.g., deep pass, short pass, or run) and its spatial trajectory (right, left, or center). The dataset for this research spans the regular NFL season data for all 32 teams from 2013 to 2022. This dataset is acquired using the nflreadr package, which conveniently extracts play-by-play data from NFL games and imports it into the R environment as structured datasets. In this study, we employ a recently developed machine learning algorithm, XGBoost. The final predictive model achieves an impressive lift of 2.61. This signifies that the presented model is 2.61 times more effective than random guessing—a significant improvement. Such a model has the potential to markedly enhance defensive coaches' ability to formulate game plans and adequately prepare their players, thus mitigating the opposing offense's yardage and point gains.

Keywords: lift, NFL, sports analytics, XGBoost

Procedia PDF Downloads 35

Authors: Lei Zhu, Nan Li

Abstract:

Cold stamping has been widely applied in the automotive industry for the mass production of a great range of automotive panels. Predicting the springback to ensure the dimensional accuracy of the cold-stamped components is a critical step. The main approaches for the prediction and compensation of springback in cold stamping include running Finite Element (FE) simulations and conducting experiments, which require forming process expertise and can be time-consuming and expensive for the design of cold stamping tools. Machine learning technologies have been proven and successfully applied in learning complex system behaviours using presentative samples. These technologies exhibit the promising potential to be used as supporting design tools for metal forming technologies. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate model to predict the springback fields for variable U-shape cold bending geometries. A dataset is created based on the U-shape cold bending geometries and the corresponding FE simulations results. The dataset is then applied to train the CNN surrogate model. The result shows that the surrogate model can achieve near indistinguishable full-field predictions in real-time when compared with the FE simulation results. The application of CNN in efficient springback prediction can be adopted in industrial settings to aid both conceptual and final component designs for designers without having manufacturing knowledge.

Keywords: springback, cold stamping, convolutional neural networks, machine learning

Procedia PDF Downloads 121

Authors: Xu Jiaqiao

Abstract:

Text sentiment analysis is an important branch of natural language processing. This technology is widely used in public opinion analysis and web surfing recommendations. At present, the mainstream sentiment analysis methods include three parts: sentiment analysis based on a sentiment dictionary, based on traditional machine learning, and based on deep learning. This paper mainly analyzes and compares the advantages and disadvantages of the SVM method of traditional machine learning and the Long Short-term Memory (LSTM) method of deep learning in the field of Chinese sentiment analysis, using Chinese comments on Sina Microblog as the data set. Firstly, this paper classifies and adds labels to the original comment dataset obtained by the web crawler, and then uses Jieba word segmentation to classify the original dataset and remove stop words. After that, this paper extracts text feature vectors and builds document word vectors to facilitate the training of the model. Finally, SVM and LSTM models are trained respectively. After accuracy calculation, it can be obtained that the accuracy of the LSTM model is 85.80%, while the accuracy of SVM is 91.07%. But at the same time, LSTM operation only needs 2.57 seconds, SVM model needs 6.06 seconds. Therefore, this paper concludes that: compared with the SVM model, the LSTM model is worse in accuracy but faster in processing speed.

Keywords: sentiment analysis, support vector machine, long short-term memory, Chinese microblog comments

Procedia PDF Downloads 61

Authors: Joseph M. Rich, Vinay A. Duddalwar, Assad A. Oberai

Abstract:

Prostate adenocarcinoma is the most common cancer in males, with osseous metastases as the commonest site of metastatic prostate carcinoma (mPC). Treatment monitoring is based on the evaluation and characterization of lesions on multiple imaging studies, including Computed Tomography (CT). Monitoring of the osseous disease burden, including follow-up of lesions and identification and characterization of new lesions, is a laborious task for radiologists. Deep learning algorithms are increasingly used to perform tasks such as identification and segmentation for osseous metastatic disease and provide accurate information regarding metastatic burden. Here, nnUNet was used to produce a model which can segment CT scan images of prostate adenocarcinoma vertebral bone metastatic lesions. nnUNet is an open-source Python package that adds optimizations to deep learning-based UNet architecture but has not been extensively combined with transfer learning techniques due to the absence of a readily available functionality of this method. The IRB-approved study data set includes imaging studies from patients with mPC who were enrolled in clinical trials at the University of Southern California (USC) Health Science Campus and Los Angeles County (LAC)/USC medical center. Manual segmentation of metastatic lesions was completed by an expert radiologist Dr. Vinay Duddalwar (20+ years in radiology and oncologic imaging), to serve as ground truths for the automated segmentation. Despite nnUNet’s success on some medical segmentation tasks, it only produced an average Dice Similarity Coefficient (DSC) of 0.31 on the USC dataset. DSC results fell in a bimodal distribution, with most scores falling either over 0.66 (reasonably accurate) or at 0 (no lesion detected). Applying more aggressive data augmentation techniques dropped the DSC to 0.15, and reducing the number of epochs reduced the DSC to below 0.1. Datasets have been identified for transfer learning, which involve balancing between size and similarity of the dataset. Identified datasets include the Pancreas data from the Medical Segmentation Decathlon, Pelvic Reference Data, and CT volumes with multiple organ segmentations (CT-ORG). Some of the challenges of producing an accurate model from the USC dataset include small dataset size (115 images), 2D data (as nnUNet generally performs better on 3D data), and the limited amount of public data capturing annotated CT images of bone lesions. Optimizations and improvements will be made by applying transfer learning and generative methods, including incorporating generative adversarial networks and diffusion models in order to augment the dataset. Performance with different libraries, including MONAI and custom architectures with Pytorch, will be compared. In the future, molecular correlations will be tracked with radiologic features for the purpose of multimodal composite biomarker identification. Once validated, these models will be incorporated into evaluation workflows to optimize radiologist evaluation. Our work demonstrates the challenges of applying automated image segmentation to small medical datasets and lays a foundation for techniques to improve performance. As machine learning models become increasingly incorporated into the workflow of radiologists, these findings will help improve the speed and accuracy of vertebral metastatic lesions detection.

Keywords: deep learning, image segmentation, medicine, nnUNet, prostate carcinoma, radiomics

Procedia PDF Downloads 67

Authors: Yehjune Heo

Abstract:

Fingerprint Anti-Spoofing approaches have been actively developed and applied in real-world applications. One of the main problems for Fingerprint Anti-Spoofing is not robust to unseen samples, especially in real-world scenarios. A possible solution will be to generate artificial, but realistic fingerprint samples and use them for training in order to achieve good generalization. This paper contains experimental and comparative results with currently popular GAN based methods and uses realistic synthesis of fingerprints in training in order to increase the performance. Among various GAN models, the most popular StyleGAN is used for the experiments. The CNN models were first trained with the dataset that did not contain generated fake images and the accuracy along with the mean average error rate were recorded. Then, the fake generated images (fake images of live fingerprints and fake images of spoof fingerprints) were each combined with the original images (real images of live fingerprints and real images of spoof fingerprints), and various CNN models were trained. The best performances for each CNN model, trained with the dataset of generated fake images and each time the accuracy and the mean average error rate, were recorded. We observe that current GAN based approaches need significant improvements for the Anti-Spoofing performance, although the overall quality of the synthesized fingerprints seems to be reasonable. We include the analysis of this performance degradation, especially with a small number of samples. In addition, we suggest several approaches towards improved generalization with a small number of samples, by focusing on what GAN based approaches should learn and should not learn.

Keywords: anti-spoofing, CNN, fingerprint recognition, GAN

Procedia PDF Downloads 161

Authors: Mohammad Didar Hossain

Abstract:

Background/Purpose: The purpose of this study was to examine the associations between productive engagements and the psychological well-being of older adults in the U.S by analyzing cross-sectional data from a secondary dataset. Specifically, this paper analyzed the associations of 4 different types of productive engagements, including current work status, caregiving to the family members, volunteering and religious strengths with the psychological well-being as an outcome variable. Methods: Data and sample: The study used the data from the Health and Retirement Study (HRS). The HRS is a nationally representative prospective longitudinal cohort study that has been conducting biennial surveys since 1992 to community-dwelling individuals 50 years of age or older on diverse issues. This analysis was based on the 2016 wave (cross-sectional) of the HRS dataset and the data collection period was April 2016 through August 2017. The samples were recruited from a multistage, national area-clustered probability sampling frame. Measures: Four different variables were considered as the predicting variables in this analysis. Firstly, current working status was a binary variable that measured by 0=Yes and 1= No. The second and third variables were respectively caregiving and volunteering, and both of them were measured by; 0=Regularly, 1= Irregularly. Finally, find in strength was measured by 0= Agree and 1= Disagree. Outcome (Wellbeing) variable was measured by 0= High level of well-being, 1= Low level of well-being. Control variables including age were measured in years, education in the categories of 0=Low level of education, 1= Higher level of education and sex r in the categories 0=male, 1= female. Analysis and Results: Besides the descriptive statistics, binary logistic regression analyses were applied to examine the association between independent and dependent variables. The results showed that among the four independent variables, three of them including working status (OR: .392, p<.001), volunteering (OR: .471, p<.003) and strengths in religion (OR .588, p<.003), were significantly associated with psychological well-being while controlling for age, gender and education factors. Also, no significant association was found between the caregiving engagement of older adults and their psychological well-being outcome. Conclusions and Implications: The findings of this study are mostly consistent with the previous studies except for the caregiving engagements and their impact on older adults’ well-being outcomes. Therefore, the findings support the proactive initiatives from different micro to macro levels to facilitate opportunities for productive engagements for the older adults, and all of these may ultimately benefit their psychological well-being and life satisfaction in later life.

Keywords: productive engagements, older adults, psychological wellbeing, productive aging

Procedia PDF Downloads 135

Authors: Hichem Sassi

Abstract:

Pneumonia, being a respiratory infection, has garnered global attention due to its rapid transmission and relatively high mortality rates. Timely detection and treatment play a crucial role in significantly reducing mortality associated with pneumonia. Presently, X-ray diagnosis stands out as a reasonably effective method. However, the manual scrutiny of a patient's X-ray chest radiograph by a proficient practitioner usually requires 5 to 15 minutes. In situations where cases are concentrated, this places immense pressure on clinicians for timely diagnosis. Relying solely on the visual acumen of imaging doctors proves to be inefficient, particularly given the low speed of manual analysis. Therefore, the integration of artificial intelligence into the clinical image diagnosis of pneumonia becomes imperative. Additionally, AI recognition is notably rapid, with convolutional neural networks (CNNs) demonstrating superior performance compared to human counterparts in image identification tasks. To conduct our study, we utilized a dataset comprising chest X-ray images obtained from Kaggle, encompassing a total of 5216 training images and 624 test images, categorized into two classes: normal and pneumonia. Employing five mainstream network algorithms, we undertook a comprehensive analysis to classify these diseases within the dataset, subsequently comparing the results. The integration of artificial intelligence, particularly through improved network architectures, stands as a transformative step towards more efficient and accurate clinical diagnoses across various medical domains.

Keywords: deep learning, computer vision, pneumonia, models, comparative study

Procedia PDF Downloads 23

Authors: Adel Edwar Waheeb Louka

Abstract:

Purpose AI-driven solutions are at the forefront of many pathology and medical imaging methods. Using algorithms designed to better the experience of medical professionals within their respective fields, the efficiency and accuracy of diagnosis can improve. In particular, X-rays are a fast and relatively inexpensive test that can diagnose diseases. In recent years, X-rays have not been widely used to detect and diagnose COVID-19. The under use of Xrays is mainly due to the low diagnostic accuracy and confounding with pneumonia, another respiratory disease. However, research in this field has expressed a possibility that artificial neural networks can successfully diagnose COVID-19 with high accuracy. Models and Data The dataset used is the COVID-19 Radiography Database. This dataset includes images and masks of chest X-rays under the labels of COVID-19, normal, and pneumonia. The classification model developed uses an autoencoder and a pre-trained convolutional neural network (DenseNet201) to provide transfer learning to the model. The model then uses a deep neural network to finalize the feature extraction and predict the diagnosis for the input image. This model was trained on 4035 images and validated on 807 separate images from the ones used for training. The images used to train the classification model include an important feature: the pictures are cropped beforehand to eliminate distractions when training the model. The image segmentation model uses an improved U-Net architecture. This model is used to extract the lung mask from the chest X-ray image. The model is trained on 8577 images and validated on a validation split of 20%. These models are calculated using the external dataset for validation. The models’ accuracy, precision, recall, f1-score, IOU, and loss are calculated. Results The classification model achieved an accuracy of 97.65% and a loss of 0.1234 when differentiating COVID19-infected, pneumonia-infected, and normal lung X-rays. The segmentation model achieved an accuracy of 97.31% and an IOU of 0.928. Conclusion The models proposed can detect COVID-19, pneumonia, and normal lungs with high accuracy and derive the lung mask from a chest X-ray with similarly high accuracy. The hope is for these models to elevate the experience of medical professionals and provide insight into the future of the methods used.

Keywords: artificial intelligence, convolutional neural networks, deeplearning, image processing, machine learningSarapin, intraarticular, chronic knee pain, osteoarthritisFNS, trauma, hip, neck femur fracture, minimally invasive surgery

Procedia PDF Downloads 25

Authors: I. V. Pinto, M. R. Sooriyarachchi

Abstract:

It can be frequently observed that the data arising in our environment have a hierarchical or a nested structure attached with the data. Multilevel modelling is a modern approach to handle this kind of data. When multilevel modelling is combined with a binary response, the estimation methods get complex in nature and the usual techniques are derived from quasi-likelihood method. The estimation methods which are compared in this study are, marginal quasi-likelihood (order 1 & order 2) (MQL1, MQL2) and penalized quasi-likelihood (order 1 & order 2) (PQL1, PQL2). A statistical model is of no use if it does not reflect the given dataset. Therefore, checking the adequacy of the fitted model through a goodness-of-fit (GOF) test is an essential stage in any modelling procedure. However, prior to usage, it is also equally important to confirm that the GOF test performs well and is suitable for the given model. This study assesses the suitability of the GOF test developed for binary response multilevel models with respect to the method used in model estimation. An extensive set of simulations was conducted using MLwiN (v 2.19) with varying number of clusters, cluster sizes and intra cluster correlations. The test maintained the desirable Type-I error for models estimated using PQL2 and it failed for almost all the combinations of MQL. Power of the test was adequate for most of the combinations in all estimation methods except MQL1. Moreover, models were fitted using the four methods to a real-life dataset and performance of the test was compared for each model.

Keywords: goodness-of-fit test, marginal quasi-likelihood, multilevel modelling, penalized quasi-likelihood, power, quasi-likelihood, type-I error

Procedia PDF Downloads 117