Search results for: Kazakh speech dataset

Authors: Natalia Kartushina

Abstract:

Foreign (second) language (L2) learning is highly promoted in modern society. Students are encouraged to study abroad (SA) to achieve the most effective learning outcomes. However, L2 learning has side effects for native language (L1) production, as L1 sounds might show a drift from the L1 norms towards those of the L2, and this, even after a short period of L2 learning. L1 assimilatory drift has been attributed to a strong perceptual association between similar L1 and L2 sounds in the mind of L2 leaners; thus, a change in the production of an L2 target leads to the change in the production of the related L1 sound. However, nowadays, it is quite common that speakers acquire two languages from birth, as, for example, it is the case for many bilingual communities (e.g., Basque and Spanish in the Basque Country). Yet, it remains to be established how FL learning affects native production in individuals who have two native languages, i.e., in simultaneous or very early bilinguals. Does FL learning (here a third language, L3) affect bilinguals’ both languages or only one? What factors determine which of the bilinguals’ languages is more susceptible to change? The current study examines the effects of L3 (English) learning on the production of vowels in the two native languages of simultaneous Spanish-Basque bilingual adolescents enrolled into the Erasmus SA English program. Ten bilingual speakers read five Spanish and Basque consonant-vowel-consonant-vowel words two months before their SA and the next day after their arrival back to Spain. Each word contained the target vowel in the stressed syllable and was repeated five times. Acoustic analyses measuring vowel openness (F1) and backness (F2) were performed. Two possible outcomes were considered. First, we predicted that L3 learning would affect the production of only one language and this would be the language that would be used the most in contact with English during the SA period. This prediction stems from the results of recent studies showing that early bilinguals have separate phonological systems for each of their languages; and that late FL learner (as it is the case of our participants), who tend to use their L1 in language-mixing contexts, have more L2-accented L1 speech. The second possibility stated that L3 learning would affect both of the bilinguals’ languages in line with the studies showing that bilinguals’ L1 and L2 phonologies interact and constantly co-influence each other. The results revealed that speakers who used both languages equally often (balanced users) showed an F1 drift in both languages toward the F1 of the English vowel space. Unbalanced speakers, however, showed a drift only in the less used language. The results are discussed in light of recent studies suggesting that the amount of language use is a strong predictor of the authenticity in speech production with less language use leading to more foreign-accented speech and, eventually, to language attrition.

Keywords: language-contact, multilingualism, phonetic drift, bilinguals' production

Procedia PDF Downloads 109

Authors: V. I. Kozyavkin, L. F. Shestopalova, T. B. Voloshyn

Abstract:

Introduction: Rehabilitation of children with Autism is the issue of the day in psychiatry and neurology. It is attributed to constantly increasing quantity of autistic children - Autistic Spectrum Disorders (ASD) Existing rehabilitation approaches in treatment of children with Autism improve their medico- social and social- psychological adjustment. Experience of treatment for different kinds of Autistic disorders in International Clinic of Rehabilitation (ICR) reveals the necessity of complex intensive approach for healing this malady and wider implementation of a Kozyavkin method for treatment of children with ASD. Methods: 19 children aged from 3 to 14 years were examined. They were diagnosed ‘Autism’ (F84.0) with comorbid neurological pathology (from pyramidal insufficiency to para- and tetraplegia). All patients underwent rehabilitation in ICR during two weeks, where INRS approach was used. INRS included methods like biomechanical correction of the spine, massage, physical therapy, joint mobilization, wax-paraffin applications. They were supplemented by art- therapy, ergotherapy, rhythmical group exercises, computer game therapy, team Olympic games and other methods for improvement of motivation and social integration of the child. Estimation of efficacy was conducted using parent’s questioning and done twice- on the onset of INRS rehabilitation course and two weeks afterward. For efficacy assessment of rehabilitation of autistic children in ICR standardized tool was used, namely Autism Treatment Evaluation Checklist (ATEC). This scale was selected because any rehabilitation approaches for the child with Autism can be assessed using it. Results: Before the onset of INRS treatment mean score according to ATEC scale was 64,75±9,23, it reveals occurrence in examined children severe communication, speech, socialization and behavioral impairments. After the end of the rehabilitation course, the mean score was 56,5±6,7, what indicates positive dynamics in comparison to the onset of rehabilitation. Generally, improvement of psychoemotional state occurred in 90% of cases. Most significant changes occurred in the scope of speech (16,5 before and 14,5 after the treatment), socialization (15.1 before and 12,5 after) and behavior (20,1 before and 17.4 after). Conclusion: As a result of INRS rehabilitation course reduction of autistic symptoms was noted. Particularly improvements in speech were observed (children began to spell out new syllables, words), there was some decrease in signs of destructiveness, quality of contact with the surrounding people improved, new skills of self-service appeared. The prospect of the study is further, according to evidence- based medicine standards, deeper examination of INRS and assessment of its usefulness in treatment for Autism and ASD.

Keywords: intensive neurophysiological rehabilitation system (INRS), international clinic od rehabilitation, ASD, rehabilitation

Procedia PDF Downloads 169

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 209

Authors: Naqeeb Ahmad Jan, Rukhsana Bibi

Abstract:

Extremism is once again pushing the globe towards ignorance and darkness. In the present day, the wave of extremist element (tendencies) has affected the people across the globe which led them to believe in manifestation of various ideologies. Likely, the Pakistan’s North-Western province (Khyber Pakhtunkhwa) served as a main prey. However, it also served as an equal partner to halt to and control the extremist activities. This current extremist element has also affected the poets herein, and thus they (poets) used their pen as a sword and depicted this havoc, the nature of extremism they witnessed, and also asked for and supported a positive and durable solution to this menace of extremism and terrorism. Their poetic works portrayed and exhibited various examples of the extremism and its possible solution to ensure peace and harmony. The researcher has taken the liberty to argue that a balanced behaviour and attitude play a key role in the fulfillment of desired actions. The imposition of any set of belief, value and attitude leads to the multiplication of extremism and it is so poisonous that it causes to the destruction of whole human society. This study has found that the present day extremism has led to the emergence of new words, similes, metaphor and other figures of speech to be a part of the language and literature to be survived. These words have been analyzed and discussed in a new getup and meanings; the similes and metaphors describing extremism used by poets and writers of this era. The methodology is based on quantitative, analytical and comparative research. Moreover, this research has discussed indication of new words and figures of speech used by the poets and which are in practice, and impacts of extremism on the modern Urdu poetry of Khyber Pakhtunkhwa.

Keywords: extremism, modern Urdu poetry, subcontinent, terrorism

Procedia PDF Downloads 262

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 75

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 108

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 87

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 154

Authors: Tami Peterson

Abstract:

Hyperbaric oxygen therapy (HBOT) has been hypothesized as an effective treatment for increasing verbal language skills in individuals on the autism spectrum. A child’s ability to effectively communicate with peers, parents, and caregivers impacts their level of independence and quality of personal relationships. This retrospective study will compare the speech development of participants aged 2-17 years that received 40 sessions of HBOT at 2.0 ATA to those who had not. Both groups will have a verbal assessment every six months. There were 31 subjects in the HBO group and 32 subjects in the non-HBO group. The statistical analysis will focus on whether hyperbaric oxygen therapy made a significant difference in Verbal Behavior Milestones Assessment and Placement Program (VB-MAPP) or Assessment of Basic Language and Learning Skills (ABLLS) results. The evidence demonstrates a strong correlation between HBOT and an increased change from baseline verbal scores compared to the control group, even in difficult to grasp areas such as spontaneous vocalization. We suggest this is due to the anti-inflammatory effects of hyperbaric oxygen therapy. Neuroinflammation causes hypoperfusion of critical central nervous system areas responsible for the symptoms described within the autism spectrum, such as problems with thought processing, memory, and speech. Decreasing the inflammation allows the brain to function properly, which results in improved verbal scores for the participants that underwent HBOT.

Keywords: assessment of basic language and learning skills, autism spectrum disorder, hyperbaric oxygen therapy, verbal behavior milestones assessment and placement program

Procedia PDF Downloads 213

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 56

Authors: Carmen Aguilera-Carnerero

Abstract:

Islamophobia, the unfounded hostility towards Muslims and Islam, has been deeply studied in the last decades from different perspectives ranging from anthropology, sociology, media studies, and linguistics. In the past few years, we have witnessed how the birth of social media has transformed formerly passive audiences into an active group that not only receives and digests information but also creates and comments publicly on any event of their interest. In this way, average citizens now have been entitled with the power of becoming potential opinion leaders. This rise of social media in the last years gave way to a different way of Islamophobia, the so called ‘cyberIslamophobia’. Considerably less attention, however, has been given to the study of islamophobic images that accompany the texts in social media. This paper attempts to analyse a corpus of 300 images of islamophobic nature taken from social media (from Twitter and Facebook) from the years 2014-2017 to see: a) how hate speech is visually constructed, b) how cyberislamophobia is articulated through images and whether there are differences/similarities between the textual and the visual elements, c) the impact of those images in the audience and their reaction to it and d) whether visual cyberislamophobia has undergone any process of permeating popular culture (for example, through memes) and its real impact. To carry out this task, we have used Critical Discourse Analysis as the most suitable theoretical framework that analyses and criticizes the dominant discourses that affect inequality, injustice, and oppression. The analysis of images was studied according to the theoretical framework provided by the visual framing theory and the visual design grammar to conclude that memes are subtle but very powerful tools to spread Islamophobia and foster hate speech under the guise of humour within popular culture.

Keywords: cyberIslamophobia, visual grammar, social media, popular culture

Procedia PDF Downloads 167

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 149

Authors: Kimberly Ho, Maeve Donnelly

Abstract:

In this paper, a speech-language pathologist (SLP) and Board Certified Behavior Analysts® (BCBA) with a combined professional experience of almost 50 years will discuss their experiences working with individuals on the autism spectrum. Some autistic children require augmentative and alternative communication (AAC) to meet their communication needs. These learners present with unique strengths and challenges, often requiring intervention from a team of professionals to generalize skills across environments. Collaboration between SLPs and BCBAs will be discussed in terms of strengths and challenges. Applied behavior analysis (ABA) will be defined and explained in the context of the treatment of learners on the autism spectrum with complex communication needs (CCN). The requirement for collaboration will be discussed by the governing boards for both BCBAs and SLPs. The strengths of each discipline will be compared along with difficulties faced when professionals experience disciplinary centrism. The challenges in teaching autistic learners with CCN will be reviewed. Case studies will be shared in which BCBAs and SLPs engage in interprofessional practice to support autistic children who use AAC to participate in a social skills group. Learner outcomes will be shared and assessed through both an SLP and BCBA perspective. Finally, ideas will be provided to promote the interprofessional practice, including establishing a shared framework, avoiding professional jargon and moving towards common terminology, and focusing on the data to ensure the efficacy of treatment.

Keywords: autism, cross disciplinary collaboration, augmentative and alternative communication, generalization

Procedia PDF Downloads 125

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 94

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 96

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 184

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 155

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 64

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 73

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 142

Authors: Maria Lita Sudo

Abstract:

The debate is an effective tool in cultivating critical thinking skills in English classes. It involves writing evidence-based arguments about a resolution in a form of constructive speech and oral discussion using constructive speech, which will then be attacked and defended. In the process of writing, EFL learners may experience anxiety, an emotional problem that affects writing achievement and cognitive processing. Thus, this study explored the sources and effect of English writing anxiety in the context of debate writing with a view to providing EFL teachers pedagogical suggestions in alleviating English writing anxiety in debate writing. The participants of this study are 95 Japanese senior high school EFL learners and 3 Japanese senior high school English teachers. In selecting the participants, opportunity sampling was employed and consent from Japanese English teachers was sought. Data were collected thru (1) observation (2) open-ended questionnaire and (3) semi-structured interview. This study revealed that not all teachers of English in the context of this study recognize the existence of English writing anxiety among their students and that the very nature of the debate, in general, may also be a source of English writing anxiety in the context of debate writing. The interview revealed that English writing anxiety affects students’ ability to retrieve L2 vocabulary. Further, this study revealed different sources of writing anxiety in debate writing, which can be categorized into four main categories: (1) L2 linguistic ability-related factors (2) instructional –related factors, (3) interpersonal-related factors, and (4) debate- related factors. Based on the findings, recommendations for EFL teachers and EFL learners in managing writing anxiety in debate writing are provided.

Keywords: debate, EFL learners, English writing anxiety, sources

Procedia PDF Downloads 137

Authors: Joselito Medina-Marin, Maria G. Serna-Diaz, Juan C. Seck-Tuoh-Mora, Norberto Hernandez-Romero, Irving Barragán-Vite

Abstract:

Wind speed forecasting is an important issue for planning wind power generation facilities. The accuracy in the wind speed prediction allows a good performance of wind turbines for electricity generation. A model based on artificial neural networks is presented in this work. A dataset with atmospheric information about air temperature, atmospheric pressure, wind direction, and wind speed in Pachuca, Hidalgo, México, was used to train the artificial neural network. The data was downloaded from the web page of the National Meteorological Service of the Mexican government. The records were gathered for three months, with time intervals of ten minutes. This dataset was used to develop an iterative algorithm to create 1,110 ANNs, with different configurations, starting from one to three hidden layers and every hidden layer with a number of neurons from 1 to 10. Each ANN was trained with the Levenberg-Marquardt backpropagation algorithm, which is used to learn the relationship between input and output values. The model with the best performance contains three hidden layers and 9, 6, and 5 neurons, respectively; and the coefficient of determination obtained was r²=0.9414, and the Root Mean Squared Error is 1.0559. In summary, the ANN approach is suitable to predict the wind speed in Pachuca City because the r² value denotes a good fitting of gathered records, and the obtained ANN model can be used in the planning of wind power generation grids.

Keywords: wind power generation, artificial neural networks, wind speed, coefficient of determination

Procedia PDF Downloads 124

Authors: Arwa Alzughaibi

Abstract:

Human Motion detection is a challenging task due to a number of factors including variable appearance, posture and a wide range of illumination conditions and background. So, the first need of such a model is a reliable feature set that can discriminate between a human and a non-human form with a fair amount of confidence even under difficult conditions. By having richer representations, the classification task becomes easier and improved results can be achieved. The Aim of this paper is to investigate the reliable and accurate human motion detection models that are able to detect the human motions accurately under varying illumination levels and backgrounds. Different sets of features are tried and tested including Histogram of Oriented Gradients (HOG), Deformable Parts Model (DPM), Local Decorrelated Channel Feature (LDCF) and Aggregate Channel Feature (ACF). However, we propose an efficient and reliable human motion detection approach by combining Histogram of oriented gradients (HOG) and local phase quantization (LPQ) as the feature set, and implementing search pruning algorithm based on optical flow to reduce the number of false positive. Experimental results show the effectiveness of combining local phase quantization descriptor and the histogram of gradient to perform perfectly well for a large range of illumination conditions and backgrounds than the state-of-the-art human detectors. Areaunder th ROC Curve (AUC) of the proposed method achieved 0.781 for UCF dataset and 0.826 for CDW dataset which indicates that it performs comparably better than HOG, DPM, LDCF and ACF methods.

Keywords: human motion detection, histograms of oriented gradient, local phase quantization, local phase quantization

Procedia PDF Downloads 257

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 194

Authors: Manjitsingh Rajput

Abstract:

Visual communication plays an important role in artificial intelligence (AI) because it enables machines to understand and interpret visual information, similar to how humans do. This abstract explores the importance of visual communication in AI and emphasizes the importance of various applications such as computer vision, object emphasis recognition, image classification and autonomous systems. In going deeper, with deep learning techniques and neural networks that modify visual understanding, In addition to AI programming, the abstract discusses challenges facing visual interfaces for AI, such as data scarcity, domain optimization, and interpretability. Visual communication and other approaches, such as natural language processing and speech recognition, have also been explored. Overall, this abstract highlights the critical role that visual communication plays in advancing AI capabilities and enabling machines to perceive and understand the world around them. The abstract also explores the integration of visual communication with other modalities like natural language processing and speech recognition, emphasizing the critical role of visual communication in AI capabilities. This methodology explores the importance of visual communication in AI development and implementation, highlighting its potential to enhance the effectiveness and accessibility of AI systems. It provides a comprehensive approach to integrating visual elements into AI systems, making them more user-friendly and efficient. In conclusion, Visual communication is crucial in AI systems for object recognition, facial analysis, and augmented reality, but challenges like data quality, interpretability, and ethics must be addressed. Visual communication enhances user experience, decision-making, accessibility, and collaboration. Developers can integrate visual elements for efficient and accessible AI systems.

Keywords: visual communication AI, computer vision, visual aid in communication, essence of visual communication.

Procedia PDF Downloads 95

Authors: Hamidreza Namazi

Abstract:

Fractal analysis is assessing fractal characteristics of data. It consists of several methods to assign fractal characteristics to a dataset which may be a theoretical dataset or a pattern or signal extracted from phenomena including natural geometric objects, sound, market fluctuations, heart rates, digital images, molecular motion, networks, etc. Fractal analysis is now widely used in all areas of science. An important limitation of fractal analysis is that arriving at an empirically determined fractal dimension does not necessarily prove that a pattern is fractal; rather, other essential characteristics have to be considered. For this purpose a Visual C++ based software called FRATSAN (FRActal Time Series ANalyser) was developed which extract information from signals through three measures. These measures are Fractal Dimensions, Jeffrey’s Measure and Hurst Exponent. After computing these measures, the software plots the graphs for each measure. Besides computing three measures the software can classify whether the signal is fractal or no. In fact, the software uses a dynamic method of analysis for all the measures. A sliding window is selected with a value equal to 10% of the total number of data entries. This sliding window is moved one data entry at a time to obtain all the measures. This makes the computation very sensitive to slight changes in data, thereby giving the user an acute analysis of the data. In order to test the performance of this software a set of EEG signals was given as input and the results were computed and plotted. This software is useful not only for fundamental fractal analysis of signals but can be used for other purposes. For instance by analyzing the Hurst exponent plot of a given EEG signal in patients with epilepsy the onset of seizure can be predicted by noticing the sudden changes in the plot.

Keywords: EEG signals, fractal analysis, fractal dimension, hurst exponent, Jeffrey’s measure

Procedia PDF Downloads 467

Authors: R. O. Osaseri, A. R. Usiobaifo

Abstract:

The power transformer which is responsible for the voltage transformation is of great relevance in the power system and oil-immerse transformer is widely used all over the world. A prompt and proper maintenance of the transformer is of utmost importance. The dissolved gasses content in power transformer, oil is of enormous importance in detecting incipient fault of the transformer. There is a need for accurate prediction of the incipient fault in transformer oil in order to facilitate the prompt maintenance and reducing the cost and error minimization. Study on fault prediction and diagnostic has been the center of many researchers and many previous works have been reported on the use of artificial intelligence to predict incipient failure of transformer faults. In this study machine learning technique was employed by using gradient decent algorithms and Support Vector Machine (SVM) in predicting incipient fault diagnosis of transformer. The method focuses on creating a system that improves its performance on previous result and historical data. The system design approach is basically in two phases; training and testing phase. The gradient decent algorithm is trained with a training dataset while the learned algorithm is applied to a set of new data. This two dataset is used to prove the accuracy of the proposed model. In this study a transformer fault diagnostic model based on Support Vector Machine (SVM) and gradient decent algorithms has been presented with a satisfactory diagnostic capability with high percentage in predicting incipient failure of transformer faults than existing diagnostic methods.

Keywords: diagnostic model, gradient decent, machine learning, support vector machine (SVM), transformer fault

Procedia PDF Downloads 322

Authors: Qasim Munye, Juned Islam, Haseeb Qureshi, Syed Jung

Abstract:

Lung nodules are commonly identified in computed tomography (CT) scans by experienced radiologists at a relatively late stage. Early diagnosis can greatly increase survival. We propose using a pix2pix conditional generative adversarial network to generate realistic images simulating early-stage lung nodule growth. We have applied deep images prior to 2341 slices from 895 computed tomography (CT) scans from the Lung Image Database Consortium (LIDC) dataset to generate pseudo-healthy medical images. From these images, 819 were chosen to train a pix2pix network. We observed that for most of the images, the pix2pix network was able to generate images where the nodule increased in size and intensity across epochs. To evaluate the images, 400 generated images were chosen at random and shown to a medical student beside their corresponding original image. Of these 400 generated images, 384 were defined as satisfactory - meaning they resembled a nodule and were visually similar to the corresponding image. We believe that this generated dataset could be used as training data for neural networks to detect lung nodules at an early stage or to improve the accuracy of such networks. This is particularly significant as datasets containing the growth of early-stage nodules are scarce. This project shows that the combination of deep image prior and generative models could potentially open the door to creating larger datasets than currently possible and has the potential to increase the accuracy of medical classification tasks.

Keywords: medical technology, artificial intelligence, radiology, lung cancer

Procedia PDF Downloads 66

Authors: Frank Adusah-Poku, John Bosco Dramani, Prince Boakye Frimpong

Abstract:

Climate change is considered a principal threat to human existence and livelihood. The persistence and intensity of droughts and floods in recent years have adversely affected food production systems and value chains, making it impossible to end global hunger by 2030. Thus, this study aims to examine the effect of climate change on food consumption for both farm and non-farm households in Ghana. An important focus of the analysis is to investigate how climate change affects alternative dimensions of food security, examine the extent to which these effects vary across heterogeneous groups, and explore the channels through which climate change affects food consumption. Finally, we conducted a pilot study to understand the significance of farm and non-farm diversification measures in reducing the harmful impact of climate change on farm households. The approach of this article is to use two secondary and one primary datasets. The first secondary dataset is the Ghana Socioeconomic Panel Survey (GSPS). The GSPS is a household panel dataset collected during the period 2009 to 2019. The second dataset is monthly district rainfall and temperature gridded data from the Ghana Meteorological Agency. This data was matched to the GSPS dataset at the district level. Finally, the primary data was obtained from a survey of farm and non-farm adaptation practices used by farmers in three regions in Northern Ghana. The study employed the household fixed effects model to estimate the effect of climate change (measured by temperature and rainfall) on food consumption in Ghana. Again, it used the spatial and temporal variation in temperature and rainfall across the districts in Ghana to estimate the household-level model. Evidence of potential mechanisms through which climate change affects food consumption was explored using two steps. First, the potential mechanism variables were regressed on temperature, rainfall, and the control variables. In the second and final step, the potential mechanism variables were included as extra covariates in the first model. The results revealed that extreme average temperature and drought had caused a decrease in food consumption as well as reduced the intake of important food nutrients such as carbohydrates, protein and vitamins. The results further indicated that low rainfall increased food insecurity among households with no education compared with those with primary and secondary education. Again, non-farm activity and silos have been revealed as the transmission pathways through which the effect of climate change on farm households can be moderated. Finally, the results indicated over 90% of the small-holder farmers interviewed had no farm diversification adaptation strategies for climate change, and a little over 50% of the farmers owned unskilled or manual non-farm economic ventures. This makes it very difficult for the majority of the farmers to withstand climate-related shocks. These findings suggest that achieving the Sustainable Development Goal of Zero Hunger by 2030 needs an integrated approach, such as reducing the over-reliance on rainfed agriculture, educating farmers, and implementing non-farm interventions to improve food consumption in Ghana.

Keywords: climate change, food consumption, Ghana, non-farm activity

Procedia PDF Downloads 6

Authors: Bernard Moeketsi Hlalele

Abstract:

Drought is a complicated natural phenomenon that creates significant economic, social, and environmental problems. An analysis of paleoclimatic data indicates that severe and extended droughts are inevitable part of natural climatic circle. This study characterised drought in Lejweleputswa using both Standardised Precipitation Index (SPI) and neural networks (NN) to quantify and predict respectively. Monthly 37-year long time series precipitation data were obtained from online NASA database. Prior to the final analysis, this dataset was checked for outliers using SPSS. Outliers were removed and replaced by Expectation Maximum algorithm from SPSS. This was followed by both homogeneity and stationarity tests to ensure non-spurious results. A non-parametric Mann Kendall's test was used to detect monotonic trends present in the dataset. Two temporal scales SPI-3 and SPI-12 corresponding to agricultural and hydrological drought events showed statistically decreasing trends with p-value = 0.0006 and 4.9 x 10⁻⁷, respectively. The study area has been plagued with severe drought events on SPI-3, while on SPI-12, it showed approximately a 20-year circle. The concluded the analyses with a seasonal analysis that showed no significant trend patterns, and as such NN was used to predict possible SPI-3 for the last season of 2018/2019 and four seasons for 2020. The predicted drought intensities ranged from mild to extreme drought events to come. It is therefore recommended that farmers, agri-business owners, and other relevant stakeholders' resort to drought resistant crops as means of adaption.

Keywords: drought, risk, neural networks, agri-businesses, project, Lejweleputswa

Procedia PDF Downloads 126