Search results for: long-term recall

Authors: James Ladzekpo

Abstract:

Background: The urgent need to identify new pharmacological targets for diabetes treatment and prevention has been amplified by the disease's extensive impact on individuals and healthcare systems. A deeper insight into the biological underpinnings of diabetes is crucial for the creation of therapeutic strategies aimed at these biological processes. Current predictive models based on genetic variations fall short of accurately forecasting diabetes. Objectives: Our study aims to pinpoint key epigenetic factors that predispose individuals to diabetes. These factors will inform the development of an advanced predictive model that estimates diabetes risk from genetic profiles, utilizing state-of-the-art statistical and data mining methods. Methodology: We have implemented a recursive feature elimination with cross-validation using the support vector machine (SVM) approach for refined feature selection. Building on this, we developed six machine learning models, including logistic regression, k-Nearest Neighbors (k-NN), Naive Bayes, Random Forest, Gradient Boosting, and Multilayer Perceptron Neural Network, to evaluate their performance. Findings: The Gradient Boosting Classifier excelled, achieving a median recall of 92.17% and outstanding metrics such as area under the receiver operating characteristics curve (AUC) with a median of 68%, alongside median accuracy and precision scores of 76%. Through our machine learning analysis, we identified 31 genes significantly associated with diabetes traits, highlighting their potential as biomarkers and targets for diabetes management strategies. Conclusion: Particularly noteworthy were the Gradient Boosting Classifier and Multilayer Perceptron Neural Network, which demonstrated potential in diabetes outcome prediction. We recommend future investigations to incorporate larger cohorts and a wider array of predictive variables to enhance the models' predictive capabilities.

Keywords: diabetes, machine learning, prediction, biomarkers

Procedia PDF Downloads 19

Authors: Lindy Adoma Dampare, Marina Aferiba Tandoh

Abstract:

Sickle cell disease (SCD) is an inherited blood disorder that mostly affects individuals in sub-Saharan Africa. Nutritional deficiencies have been well established in SCD patients. In Ghana, studies have revealed the prevalence of malnutrition, especially amongst children with SCD and hence the need to develop an evidence-based comprehensive nutritional therapy for SCD to improve their nutritional status. The aim of the study was to develop and assess the effect of a nutrition education material on the nutritional status of SCD patients in Ghana. This was a pre-post interventional study. Patients between the ages of 2 to 60 years were recruited from the Tema General Hospital. Following a baseline nutrition knowledge (NK), beliefs, sanitary practice and dietary consumption pattern assessment, a twice-monthly nutrition education was carried out for 3 months, followed by a post-intervention assessment. Nutritional status of SCD patients was assessed using a 3-days dietary recall and anthropometric measurements. Nutrition education (NE) was given to SCD adults and caregivers of SCD children. Majority of the caregivers (69%) and SCD adult (82%) at baseline had low NK. The level of NK improved significantly in SCD adults (4.18±1.83 vs. 10.00±1.00, p<0.001) and caregivers (5.58 ± 2.25 vs.10.44± 0.846, p<0.001) after NE. Increase in NK improved dietary intake and dietary consumption pattern of SCD patients. Significant increase in weight (23.2±11.6 vs. 25.9±12.1, p=0.036) and height (118.5±21.9 vs. 123.5±22.2, p=0.011) was observed in SCD children at post intervention. Stunting (10.5% vs. 8.6%, p=0.62) and wasting (22.1% vs. 14.4%, p=0.30) reduced in SCD children after NE although not statistically significant. Reduction (18.2% vs. 9.1%) in underweight and an increase (18.2% vs. 27.3%) in overweight SCD adults was recorded at post intervention. Fat mass remained the same while high muscle mass increased (18.2% vs. 27.3%) at post intervention in SCD adult. Anaemic status of SCD patients improved at post intervention and the improvement was statistically significant amongst SCD children. Nutrition education improved the NK of SCD caregivers and adults hence, improving the dietary consumption pattern and nutrient intake of SCD patients. Overall, NE improved the nutritional status of SCD patients. This study shows the potential of nutrition education in improving the nutritional knowledge, dietary consumption pattern, dietary intake and nutritional status of SCD patients, and should be further explored.

Keywords: sickle cell disease, nutrition education, dietary intake, nutritional status

Procedia PDF Downloads 69

Authors: Daria Druzhinenko- Silhan, Patrick Schmoll

Abstract:

Childhood obesity is one of the important problem in domain of health care. During two recent decades we are observing a real epidemic of this noninfectious illness. Its consequences are hard: cardio-vascular disease; diabetes; arthrosis etc. (OMS, 2012) Keep Healthy Kids  » study aims to create a new system of accompanying of childhood obesity based on new technologies as mobile applications or serious video-games. We realize a support-study which aims to understand motivations, psychological dynamite and family's impact on weight-loss process in childhood. Sample: 65 children from 7 to 10 years old accompanied by special Care Center in France. Methodology: we proceed by an innovative approach that bases on quantitative and qualitative methods of data collection. We focus our proposal on data collected from medical files. We are also realizing individual assessment (still ongoing) that aims to understand psychological profiles of obese children and their family dynamic. Results: Only 16,9% of children asked for medical accompanying of obesity. We noted that the most important reason to come to the care Center was the fact of mates' scoffs (46,2%°), the second one was the appearance or look (40 %). We found out that the self-image of these children in self-evaluation questionnaire was described mostly as rather good (46,2) or good (28,2%); the most part of children evaluated their well-being as rather good (29,7%) or good (51,4%). In interviews children had tendency to not recall why they came to the Care Center. Discussion : These results permit us to make a hypothesis that children suffering of overweight or obesity are not clearly aware why they must loose weight. It was rather the peer environment that pointed out the problem of overweight for them. So the motivation to loose weight is mostly supported by environment. We suppose that it is a « weak-point » of their motivation and it can be over-come using serious video-games supporting physical activity that can make deviate the motivation from « to loose weight for be looked better by the others » into « have fun and feeling me better ».

Keywords: childhood obesity, motivation, weight-loss, serious video-game

Procedia PDF Downloads 282

Authors: Kehinde Agbele, Longe Olumide, Daniel Ekong, Dele Seluwa, Akintoye Onamade

Abstract:

One major problem of most existing information retrieval systems (IRS) is that they provide even access and retrieval results to individual users specially based on the query terms user issued to the system. When using IRS, users often present search queries made of ad-hoc keywords. It is then up to IRS to obtain a precise representation of user’s information need, and the context of the information. In effect, the volume and range of the Internet documents is growing exponentially and consequently causes difficulties for a user to obtain information that precisely matches the user interest. Diverse combination techniques are used to achieve the specific goal. This is due, firstly, to the fact that users often do not present queries to IRS that optimally represent the information they want, and secondly, the measure of a document's relevance is highly subjective between diverse users. In this paper, we address the problem by investigating the optimization of IRS to individual information needs in order of relevance. The paper addressed the development of algorithms that optimize the ranking of documents retrieved from IRS. This paper addresses this problem with a two-fold approach in order to retrieve domain-specific documents. Firstly, the design of context of information. The context of a query determines retrieved information relevance using personalization and context-awareness. Thus, executing the same query in diverse contexts often leads to diverse result rankings based on the user preferences. Secondly, the relevant context aspects should be incorporated in a way that supports the knowledge domain representing users’ interests. In this paper, the use of evolutionary algorithms is incorporated to improve the effectiveness of IRS. A context-based information retrieval system that learns individual needs from user-provided relevance feedback is developed whose retrieval effectiveness is evaluated using precision and recall metrics. The results demonstrate how to use attributes from user interaction behavior to improve the IR effectiveness.

Keywords: context, document relevance, information retrieval, personalization, user search behaviors

Procedia PDF Downloads 434

Authors: Mst Shapna Akter, Hossain Shahriar

Abstract:

One of the most important challenges in the field of software code audit is the presence of vulnerabilities in software source code. Every year, more and more software flaws are found, either internally in proprietary code or revealed publicly. These flaws are highly likely exploited and lead to system compromise, data leakage, or denial of service. C and C++ open-source code are now available in order to create a largescale, machine-learning system for function-level vulnerability identification. We assembled a sizable dataset of millions of opensource functions that point to potential exploits. We developed an efficient and scalable vulnerability detection method based on deep neural network models that learn features extracted from the source codes. The source code is first converted into a minimal intermediate representation to remove the pointless components and shorten the dependency. Moreover, we keep the semantic and syntactic information using state-of-the-art word embedding algorithms such as glove and fastText. The embedded vectors are subsequently fed into deep learning networks such as LSTM, BilSTM, LSTM-Autoencoder, word2vec, BERT, and GPT-2 to classify the possible vulnerabilities. Furthermore, we proposed a neural network model which can overcome issues associated with traditional neural networks. Evaluation metrics such as f1 score, precision, recall, accuracy, and total execution time have been used to measure the performance. We made a comparative analysis between results derived from features containing a minimal text representation and semantic and syntactic information. We found that all of the deep learning models provide comparatively higher accuracy when we use semantic and syntactic information as the features but require higher execution time as the word embedding the algorithm puts on a bit of complexity to the overall system.

Keywords: cyber security, vulnerability detection, neural networks, feature extraction

Procedia PDF Downloads 45

Authors: Allioua Meryem

Abstract:

Similar to much of the developing world, Algeria is currently undergoing an epidemiological transition. While mal- and under-nutrition and infectious diseases used to be the main causes of poor health, today there is a higher proportion of chronic, non-communicable diseases (NCDs), including cardiovascular disease, diabetes mellitus, cancer, etc. According to estimates for Algeria from the World Health Organization (WHO), NCDs accounted for 63% of all deaths in 2010. The objective of this study was the assessment of eating habits and anthropometric characteristics in a group of youth aged 15 to 19 years in Tlemcen. This study was conducted on a total effective of 806 youth enrolled in a descriptive cross-sectional study; the classification of nutritional status has been established by international standards IOTF, youth were defined as obese if they had a BMI ≥ 95th percentile, and youth with 85th ≤ BMI ≤ 95th percentile were defined as overweight. Wc is classified by the criteria HD, Wc with moderate risk ≥ 90th percentile and Wc with high risk ≥ 95th percentile. The dietary assessment was based on a 24-hour dietary recall assisted by food records. USDA’S nutrient database for Nutrinux® program was used to analyze dietary intake. Nutrients adequacy ratio was calculated by dividing daily individual intake to dietary recommended intake DRI for each nutrient. 9% of the population was overweight, 3% was obese, 7.5% had abdominal obesity, foods eaten in moderation are chips, cookies, chocolate 1-3 times/day and increased consumption of fried foods in the week, almost half of youth consume sugary drinks more than 3 times per week, we observe a decreased intake of energy, protein (P < 0.001, P = 0.003), SFA (P = 0.018), the NAR of phosphorus, iron, magnesium, vitamin B6, vitamin E, folate, niacin, and thiamin reflecting less consumption of fruit, vegetables, milk, and milk products. Youth surveyed have eating habits at risk of developing obesity and chronic disease.

Keywords: food intake, health, anthropometric characteristics, Algeria

Procedia PDF Downloads 502

Authors: Patrick Mkhanyiseli Zimu

Abstract:

A sedentary lifestyle and insufficient physical activity (PA) increases the risk of developing chronic non-communicable diseases (NCDs). Knowing the PA levels and patterns of adolescents from different socio-economic backgrounds is important to direct programs at schools and in communities to prevent NCDs risk factors, which can have long-term effects on the health of the adolescents. The study aimed to investigate adolescent PA levels, patterns, and influencing factors (age, gender, socio-economic status). The 353 participants (203 females and 150 males) from eight low socio-economic (LSES) and middle socio-economic (MSES) public secondary schools completed a Physical Activity Questionnaire for Adolescents (PAQ-A). The PAQ-A is a seven day recall instrument that assesses general estimates of PA levels and patterns for high school learners in Grades 9-12 and provides a summary of physical activity scores derived from seven items, each scored on a 5-point Likert scale. The seven items were PA during spare time and five domains (during physical education, lunch break, after school, in the evenings, on the weekend) and selecting one statement that described participant’s physical activity behaviour. The PA Levels (x̄=2.61, SD=.74) were below the international PA cut-off points of x̄=2.75. Physical education (PE) showed the highest PA score (x̄=3.05, SD=1.21) and lunch break showed the lowest PA score (x̄=2.09, SD=1.14). Positive correlations occurred between PA levels and SES (r=.122, p=0.022), and PA and gender (r=.223, p= 0.0001). LSES participant’s PA score was significantly lower (x̄=2.52; SD=.73) than those from MSES (x̄=2.70; SD=.74, p=0.022). Adolescents from low and middle socio-economic status communities are not sufficiently active. Their average PA score of 2.61 is below the PAQ-A global criterion referenced cut-off points of 2.75, which is considered sufficiently physically active for adolescents to ensure both short- and long-term health benefits. As adolescents are not sufficiently active, collaborative school and community PA programs need to be implemented to supplement physical education in order to prevent short- and long-term health problems.

Keywords: adolescents, health promotion, physical activity, physical education

Procedia PDF Downloads 67

Authors: Patricia Portugal Marques de Carvalho Lourenco

Abstract:

A three-phase methodological multi-lingual path was designed, constructed and carried out using the 2020 Chinese Internet Drama Series We Are All Alone as a case study. Phase one, the backbone of the research, comprised of secondary data analysis, providing the structure on which the next two phases would be built on. Phase one incorporated a Google Scholar and a Baidu Index analysis, Star Network Influence Index and Mydramalist.com top two drama reviews, along with an article written about the drama and scrutiny of Chinese related blogs and websites. Phase two was field research elaborated across Latin Europe, and phase three was social media focused, having into account that perceptions are going to be memory conditioned based on past ideas recall. Overall, research has shown the poor cultural expression of Chinese entertainment in Latin Europe and demonstrated the inexistence of Chinese content in French, Italian, Portuguese and Spanish Business to Consumer retailers; a reflection of their low significance in Latin European markets and the short-life cycle of entertainment products in general, bubble-gum, disposable goods without a mid to long-term effect in consumers lives. The process of conducting comprehensive international research was complex and time-consuming, with data not always available in Mandarin, the researcher’s linguistic deficiency, limited Chinese Cultural Knowledge and cultural equivalence. Despite steps being taken to minimize the international proposed research, theoretical limitations concurrent to Latin Europe and China still occurred. Data accuracy was disputable; sampling, data collection/analysis methods are heterogeneous; ascertaining data requirements and the method of analysis to achieve a construct equivalence was challenging and morose to operationalize. Secondary data was also not often readily available in Mandarin; yet, in spite of the array of limitations, research was done, and results were produced.

Keywords: research methodologies, international research, primary data, secondary data, research limitations, online dramas, china, latin europe

Procedia PDF Downloads 45

Authors: Munkhtuul G., Bolortsetseg Z., Lutzul M., Sugar N., Nyamdorj D., Nomundari B., Zesemdorj O., Erdenebayar N., Lkhagvasuren T. S., Munkhbayarlakh S., Bayasgalan T. Uurtuya S. H.

Abstract:

Background: Elevated serum uric acid (SUA) levels are observed in metabolic and cardiovascular conditions as an early predictor of metabolic syndrome (MS). Hyperuricemia, characterised by high uric acid levels in serum, increases the risk of developing MS by 1.6 times. Being overweight and obese significantly contributes to developing MS and cardiovascular disorders. In Mongolia, the prevalence of overweight and obesity is reaching 48.8% among individuals aged 15 to 49 years, indicating a potential surge in the incidence of MS, cardiovascular disorders, diabetes mellitus, and gout.Objective: This study aimed to determine the SUA levels in men diagnosed with MS and investigate the factors influencing these levels.Methods: A total of 119 men aged 30-60, who underwent preventive examinations and resided in Ulaanbaatar city, were included in the study. The criteria established by the International Diabetes Federation (IDF), American Heart Association (AHA), and the National Heart, Lung, and Blood Institute (NHLBI) were employed to define metabolic syndrome. Hyperuricemia was defined as SUA levels ≥7 mg/dL. Dietary intake was evaluated through the 24-hour recall method.Results: The study revealed that the prevalence of MS among the participants was 42.9% (n=51), with hyperuricemia observed in 16.8% (n=20) of the individuals. Among men diagnosed with MS, 21.3% (n=10) exhibited hyperuricemia. The mean SUA levels were as follows: 4.7±0.8 mg/dL in the healthy group, 5.9±1.1 mg/dL in men without MS but presenting central obesity, and 6.2±1.3 mg/dL in men with MS. After adjusting for age and body mass index (BMI), a positive correlation was observed between SUA levels and triglycerides (β=0.93) as well as lipid accumulation product (LAP) (β=0.92) in men with MS. In the central obesity group, SUA levels exhibited a positive correlation with triglycerides (β=0.91), visceral adiposity index (VAI) (β=0.73), LAP (β=0.92), and cardiometabolic index (CMI) (β=0.69). The risk of hyperuricemia increased by 3.29 times with elevated triglycerides and 3.53 times with an increased LAP.Conclusion: The findings indicate that abdominal fat accumulation, as indicated by elevated triglyceride levels and LAP, is associated with increased SUA levels in men with MS. However, no significant relationship was observed between SUA levels and dietary intake.

Keywords: central obesity, obesity, triglycerides, hyperuricemia

Procedia PDF Downloads 38

Authors: Mpho Mokoatle, Darlington Mapiye, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on $k$-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0%, 80.5%, 80.5%, 63.6%, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms.

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 133

Authors: Darlington Mapiye, Mpho Mokoatle, James Mashiyane, Stephanie Muller, Gciniwe Dlamini

Abstract:

Great advances in high-throughput sequencing technologies have resulted in availability of huge amounts of sequencing data in public and private repositories, enabling a holistic understanding of complex biological phenomena. Sequence data are used for a wide range of applications such as gene annotations, expression studies, personalized treatment and precision medicine. However, this rapid growth in sequence data poses a great challenge which calls for novel data processing and analytic methods, as well as huge computing resources. In this work, a machine and statistical learning approach for DNA sequence classification based on k-mer representation of sequence data is proposed. The approach is tested using whole genome sequences of Mycobacterium tuberculosis (MTB) isolates to (i) reduce the size of genomic sequence data, (ii) identify an optimum size of k-mers and utilize it to build classification models, (iii) predict the phenotype from whole genome sequence data of a given bacterial isolate, and (iv) demonstrate computing challenges associated with the analysis of whole genome sequence data in producing interpretable and explainable insights. The classification models were trained on 104 whole genome sequences of MTB isoloates. Cluster analysis showed that k-mers maybe used to discriminate phenotypes and the discrimination becomes more concise as the size of k-mers increase. The best performing classification model had a k-mer size of 10 (longest k-mer) an accuracy, recall, precision, specificity, and Matthews Correlation coeffient of 72.0 %, 80.5 %, 80.5 %, 63.6 %, and 0.4 respectively. This study provides a comprehensive approach for resampling whole genome sequencing data, objectively selecting a k-mer size, and performing classification for phenotype prediction. The analysis also highlights the importance of increasing the k-mer size to produce more biological explainable results, which brings to the fore the interplay that exists amongst accuracy, computing resources and explainability of classification results. However, the analysis provides a new way to elucidate genetic information from genomic data, and identify phenotype relationships which are important especially in explaining complex biological mechanisms

Keywords: AWD-LSTM, bootstrapping, k-mers, next generation sequencing

Procedia PDF Downloads 123

Authors: Farzaneh Badinlou, Reza Kormi-Nouri, Monika Knopf, Kamal Kharazi

Abstract:

Research into long-term memory has demonstrated that the richness of the knowledge base cues in memory tasks improves retrieval process, which in turn influences learning and memory performance. The present research investigated the idea that adding cues connected to knowledge can affect memory performance in the context of action memory in children. In action memory studies, participants are instructed to learn a series of verb–object phrases as verbal learning and experience-based learning (learning by doing and learning by observation). It is well established that executing action phrases is a more memorable way to learn than verbally repeating the phrases, a finding called enactment effect. In the present study, a total of 410 students from four grade groups—2nd, 4th, 6th, and 8th—participated in this study. During the study, participants listened to verbal action phrases (VTs), performed the phrases (SPTs: subject-performed tasks), and observed the experimenter perform the phrases (EPTs: experimenter-performed tasks). During the test phase, cued recall test was administered. Semantic relational cues (i.e., well-integrated vs. poorly integrated items) were manipulated in the present study. In that, the participants were presented two lists of action phrases with high semantic integration between verb and noun, e.g., “write with the pen” and with low semantic integration between verb and noun, e.g., “pick up the glass”. Results revealed that experience-based learning had a better results than verbal learning for both well-integrated and poorly integrated items, though manipulations of semantic relational cues can moderate the enactment effect. In addition, children of different grade groups outperformed for well- than poorly integrated items, in flavour of older children. The results were discussed in relation to the effect of knowledge-based information in facilitating retrieval process in children.

Keywords: action memory, enactment effect, knowledge-based cues, school-aged children, semantic relational cues

Procedia PDF Downloads 250

Authors: Nazia Shehzad

Abstract:

Language and art can supplement and correlate each other. Through the ages art has been a means of visual expression used to convey a wide series of incarnated ideas. Art can take the perceiver into different times and into different worlds. It can also be used to introduce different levels of vocabulary to the learners of a second language. Learning a second language for most students is a very difficult and strenuous experience. They are not only trying to accommodate to a new language but are also trying to adjust to themselves and a new environment. They are anxious about almost everything, but they are especially self-conscious about their performance in the classroom. By relocating the focus from the student to an object, everyone participates, thus waiving a certain degree of self-consciousness. The experience, a student has with art in the classroom has to be gratifying for both the student and the teacher. If the atmosphere in the classroom is too grave it will not serve any useful purpose. Art is an excellent way to teach English and encourage collaboration and interaction between students of all ages. As making art involves many different processes, it is wonderful for classification and following/giving instructions. It is also an effective way to achieve and implement language of characterization and comparison and vocabulary acquirement for the elements of design (shape, size, color, texture, tone etc.) is so much more entertaining if done in a practical and hands-on way. Expressing ideas and feelings through art is also of immeasurable value where students are at the beginning stages of English language acquisition and for many of my Saudi students it was a form of therapy. It is also a way to respect, search, examine and share the cultural traditions of different cultures, and of the students themselves. Art not only provides a field for ideas to keep aimless, meandering minds of students' busy but is also a productive tool to analyze English language in a new order. As an ESL teacher, using art is a highly compelling way to bridge the gap between student and teacher. It’s difficult to keep students concentrated, especially when they speak a different language. To get students to actually learn and explore something in your foreign language lesson, artwork is your best friend. Many teachers feel that through amalgamation of the arts into their academic lessons students are able to learn more profoundly because they use diverse ways of thinking and problem solving. Teachers observe that drawing often retains students who might otherwise be dispassionate and can help students move ahead simple recall when they are asked to make connections and come up with an exclusive interpretation through an artwork or drawing. Students use observation skills when they are drawing, and this can help to persuade students who might otherwise remain silent or need more time to process information.

Keywords: amalgamation of arts, expressing ideas and feelings through arts, effective way to achieve and implement language, language and art can supplement and correlate each other

Procedia PDF Downloads 333

Authors: Ananya Gupta, Sangeeta Bhaskar

Abstract:

Mycobacterium indicus pranii (MIP) is a saprophytic mycobacterium. It is a predecessor of M. avium complex (MAC). Whole genome analysis and growth kinetics studies have placed MIP in between pathogenic and non-pathogenic species. It shares significant antigenic repertoire with M. tuberculosis and have unique immunomodulatory properties. MIP provides better protection than BCG against pulmonary tuberculosis in animal models. Immunization with MIP by aerosol route provides significantly higher protection as compared to immunization by subcutaneous (s.c.) route. However, mechanism behind differential protection has not been studied. In this study, using mice model we have evaluated and compared the M.tb specific immune response in lung compartments (airway lumen / lung interstitium) as well as spleen following MIP immunization via nasal (i.n.) and s.c. route. MIP i.n. vaccination resulted in increased seeding of memory T cells (CD4+ and CD8+ T-cells) in the airway lumen. Frequency of CD4+ T cells expressing Th1 migratory marker (CXCR3) and activation marker (CD69) were also high in airway lumen of MIP i.n. group. Significantly high ex vivo secretion of cytokines- IFN-, IL-12, IL-17 and TNF- from cells of airway luminal spaces provides evidence of antigen-specific lung immune response, besides generating systemic immunity comparable to MIP s.c. group. Analysis of T cell response on per cell basis revealed that antigen specific T-cells of MIP i.n. group were functionally superior as higher percentage of these cells simultaneously secreted IFN-gamma, IL-2 and TNF-alpha cytokines as compared to MIP s.c. group. T-cells secreting more than one of the cytokines simultaneously are believed to have robust effector response and crucial for protection, compared with single cytokine secreting T-cells. Adoptive transfer of airway luminal T-cells from MIP i.n. group into trachea of naive B6 mice revealed that MIP induced CD8 T-cells play crucial role in providing long term protection. Thus the study demonstrates that MIP intranasal vaccination induces M.tb specific memory T-cells in the airway lumen that results in an early and robust recall response against M.tb infection.

Keywords: airway lumen, Mycobacterium indicus pranii, Th1 migratory markers, vaccination

Procedia PDF Downloads 159

Authors: Chamika Chiran Perera, Dananjaya Perera, Chirath Dasanayake, Banuka Athuraliya

Abstract:

Male infertility is a major problem in the world, and it is a neglected and sensitive health issue in Sri Lanka. It can be determined by analyzing human semen samples. Sperm motility is one of many factors that can evaluate male’s fertility potential. In Sri Lanka, this analysis is performed manually. Manual methods are time consuming and depend on the person, but they are reliable and it can depend on the expert. Machine learning and deep learning technologies are currently being investigated to automate the spermatozoa motility analysis, and these methods are unreliable. These automatic methods tend to produce false positive results and false detection. Current automatic methods support different techniques, and some of them are very expensive. Due to the geographical variance in spermatozoa characteristics, current automatic methods are not reliable for motility analysis in Sri Lanka. The suggested system, DeepMotile, is to explore a method to analyze motility of human spermatozoa automatically and present it to the andrology laboratories to overcome current issues. DeepMotile is a novel deep learning method for analyzing spermatozoa motility parameters in the Sri Lankan population. To implement the current approach, Sri Lanka patient data were collected anonymously as a dataset, and glass slides were used as a low-cost technique to analyze semen samples. Current problem was identified as microscopic object detection and tackling the problem. YOLOv5 was customized and used as the object detector, and it achieved 94 % mAP (mean average precision), 86% Precision, and 90% Recall with the gathered dataset. StrongSORT was used as the object tracker, and it was validated with andrology experts due to the unavailability of annotated ground truth data. Furthermore, this research has identified many potential ways for further investigation, and andrology experts can use this system to analyze motility parameters with realistic accuracy.

Keywords: computer vision, deep learning, convolutional neural networks, multi-target tracking, microscopic object detection and tracking, male infertility detection, motility analysis of human spermatozoa

Procedia PDF Downloads 69

Authors: Monica Karlsson

Abstract:

The positive effect of a supportive written context on comprehension and retention when faced with a previously unknown idiomatic expression is today an indisputable fact, especially if relevant clues are given in close proximity of the item in question. Also, giving learners a chance of visualizing the meaning of an idiom by offering them its source domain and/or by elaborating etymologically, i.e. providing a mental picture in addition to the spoken/written form (referred to as dual coding), seems to enhance comprehension and retention even further, especially if the idiom is of a more transparent kind. For example, by explaining that walk the plank has a maritime origin and a canary in a coal mine comes from the time when canaries were kept in cages to warn miners if gas was leaking out at which point the canaries succumbed immediately, learners’ comprehension and retention have been shown to increase. The present study aims to investigate whether contextualization of an audiovisual kind could help increase comprehension and retention of L2 idioms. 40 Swedish first-term university students studying English as part of their education to become middle-school teachers participated in the investigation, which tested 24 idioms, all of which were ascertained to be previously unknown to the informants. While half of the learners were subjected to a test in which they were asked to watch scenes from various TV programmes, each scene including one idiomatic expression in a supportive context, the remaining 20 students, as a point of reference, were only offered written contexts, though equally supportive. Immediately after these sessions, both groups were given the same idioms in a decontextualized form and asked to give their meaning. After five weeks, finally, the students were subjected to yet another decontextualized comprehension test. Furthermore, since mastery of idioms in one’s L1 appears to correlate to a great extent with a person’s ability to comprehend idioms in an L2, all the informants were also asked to take a test focusing on idioms in their L1. The result on this test is thus seen to indicate each student’s potential for understanding and memorizing various idiomatic expressions from a more general perspective. Preliminary results clearly show that audiovisual contextualization indeed has a positive effect on learners’ retention. In addition, preliminary results also show that those learners’ who were able to recall most meanings were those who had a propensity for idiom comprehension in their L1.

Keywords: English, L2, idioms, audiovisual context

Procedia PDF Downloads 314

Authors: Ashi Gautam, Isha Shukla, Akhil Seghal

Abstract:

Biosensors are analytical devices that use a biological sensing element to detect and measure a specific chemical substance or biomolecule in a sample. These devices are widely used in various fields, including medical diagnostics, environmental monitoring, and food analysis, due to their high specificity, sensitivity, and selectivity. In this research paper, a machine learning model is proposed for predicting the suitability of skin care products based on biosensor readings. The proposed model takes in features extracted from biosensor readings, such as biomarker concentration, skin hydration level, inflammation presence, sensitivity, and free radicals, and outputs the most appropriate skin care product for an individual. This model is trained on a dataset of biosensor readings and corresponding skin care product information. The model's performance is evaluated using several metrics, including accuracy, precision, recall, and F1 score. The aim of this research is to develop a personalised skin care product recommendation system using biosensor data. By leveraging the power of machine learning, the proposed model can accurately predict the most suitable skin care product for an individual based on their biosensor readings. This is particularly useful in the skin care industry, where personalised recommendations can lead to better outcomes for consumers. The developed model is based on supervised learning, which means that it is trained on a labeled dataset of biosensor readings and corresponding skin care product information. The model uses these labeled data to learn patterns and relationships between the biosensor readings and skin care products. Once trained, the model can predict the most suitable skin care product for an individual based on their biosensor readings. The results of this study show that the proposed machine learning model can accurately predict the most appropriate skin care product for an individual based on their biosensor readings. The evaluation metrics used in this study demonstrate the effectiveness of the model in predicting skin care products. This model has significant potential for practical use in the skin care industry for personalised skin care product recommendations. The proposed machine learning model for predicting the suitability of skin care products based on biosensor readings is a promising development in the skin care industry. The model's ability to accurately predict the most appropriate skin care product for an individual based on their biosensor readings can lead to better outcomes for consumers. Further research can be done to improve the model's accuracy and effectiveness.

Keywords: biosensors, data model, machine learning, skin care

Procedia PDF Downloads 47

Authors: Kim Jin-OK, Lee Jin-Eui, Han Seung-Hoon, Kim Nam-Jo

Abstract:

This study aimed to analyze the effect of the motivation of Chinese tourists to visit North Korea on their decision making process. Chinese tourists account for a considerable portion of foreign tourists in the world, while North Korea is the favorite tourist attraction of Chinese tourists. The motivation to visit North Korea was divided into three factors: the redness, which is the modern cultural heritage of Communism based on the red tourism accounting for the significant portion of domestic tourism, the novelty of the special environment of North Korean society, and the convenience of tour to North Korea in terms of geographical distance and policy of China. Red tourism refers to visiting the places of revolutionary events, monuments, artifacts and the residences of previous communist leaders, and other places related to the past Chinese Communist Party. As a revolutionary tourism, red tourism has recently been taking place in the old communist countries to recall their memories on the revolutionary places in China, as well as in North Korea, Vietnam, Cambodia, Russia, Bulgaria, Cuba, etc. In order to examine the effect of the segmented motivations on the revisit intention of Chinese tourists who have experienced a tour to North Korea, this study employed the model of goal-directed behavior, a model developed by adding a variable of emotion to the theory of planned behavior, which has a strong explanatory power on the decision making process of people in social science. For achieving the aim of the study, the data was collected through the survey in Dandong, China against Chinese tourists who have visited North Korea. The results of this study found that not only the novelty of North Korea, but also the redness, which accounts for the largest proportion in the domestic tourism, are significantly affecting overseas tour of Chinese tourists at this time point where overseas tour of Chinese tourists continue to increase. The results, therefore, suggest that the old communist countries, including those in Asia, need an emotional promotion strategy that stimulates nostalgia by focusing on the redness of the modern cultural heritage of Communism to attract Chinese tourists.

Keywords: model of goal-directed behavior, modern cultural heritage, North Korea, red tourism

Procedia PDF Downloads 281

Authors: Bartłomiej K. Sołtysik, Agnieszka Guligowska, Łukasz Kroc, Małgorzata Pigłowska, Elizavetta Fife, Tomasz Kostka

Abstract:

Introduction: Functional capacity is one of the basic determinants of health in older age. Functional capacity may be influenced by multiple disorders, including cardiovascular and metabolic diseases. Nevertheless, there is relatively little evidence regarding the association of functional status and cardiometabolic risk factors. Aim: The aim of this research is to check possible association between functional capacity and cardiovascular risk factor in a group of younger seniors. Materials and Methods: The study group consisted of 300 participants aged 60-65 years (50% were women). Total cholesterol (TC), triglycerides (TG), high density lipoprotein cholesterol (HDL-C), low density lipoprotein cholesterol (LDL-C), glucose, uric acid, body mass index (BMI), waist-to-height ratio (WHtR) and blood pressure were measured. Smoking status and physical activity level (by Seven Day Physical Activity Recall Questionnaire ) were analysed. Functional status was assessed with the Timed Up and Go (TUG) Test. The data were compared according to gender, and then separately for both sexes regarding prolonged TUG score (>7 s). The limit of significance was set at p≤0.05 for all analyses. Results: Women presented with higher serum lipids and longer TUG. Men had higher blood pressure, glucose, uric acid, the prevalence of hypertension and history of heart infarct. In women group, those with prolonged TUG displayed significantly higher obesity rate (BMI, WHTR), uric acid, hypertension and ischemic heart disease (IHD), but lower physical activity level, TC or LDL-C. Men with prolonged TUG were heavier smokers, had higher TG, lower HDL and presented with higher prevalence of diabetes and IHD. Discussion: This study shows association between functional status and risk profile of cardiometabolic disorders. In women, the relationship of lower functional status to cardiometabolic diseases may be mediated by overweight/obesity. In men, locomotor problems may be related to smoking. Higher education level may be considered as a protective factor regardless of gender.

Keywords: cardiovascular risk factors, functional capacity, TUG test, seniors

Procedia PDF Downloads 267

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: Marina Aferiba Tandoh, Elsie Odei

Abstract:

Peptic Ulcer Disease (PUD) is amongst the commonest gastrointestinal problems that require emergency treatment in order to preserve life. The prevalence of PUD is increasing within the Ghanaian population, deepening the need to identify factors that are associated with its occurrence. This cross-sectional study assessed the nutritional status, socioeconomic and lifestyle factors associated with PUD among patients attending the Out-Patient Department of the Tema General Hospital of Ghana. A food frequency questionnaire and a three-day, 24-hour recall were used to assess the dietary intakes of study participants. A standardized questionnaire was used to obtain information on the participants’ socio-demographic characteristics, lifestyle as well as medical history. The data was analyzed using SPSS version 22. The mean age of study participants was 32.8±15.41years. Females were significantly higher (61.4%) than males (38.6%) (p < 0.001). All participants had received some form of education, with tertiary education being the highest (52.6%). The majority of them managed their condition with medications only (86%), while 10.5% managed it with a combination of medications and diet. The rest were either by dietary counseling only (1.8%), or surgery only (1.8%). or herbal medicines (29.3%), which were made from home (7.2%) or bought from a medical store (10.8%). Most of the participants experienced a recurrence of the disease (42.1%). For those who had ever experienced recurrences of the disease, it happened when they ate acidic foods (1.8%), ate bigger portions (1.8%), starved themselves (1.8%), or were stressed (1.8%). Others also had triggers when they took certain medications (1.8%) or ate too much pepper (1.8%). About 49% of the participants were either overweight or obese with a recurrence of PUD (p>0.05). Obese patients had the highest rate of PUD recurrences (41%). Drinking alcohol was significantly associated with the recurrence of PUD (χ2= 5.243, p=0.026). Other lifestyles, such as weed smoking, fasting, and use of herbal medicine and NSAIDs did not have any significant association with the disease recurrence. There was no significant correlation between the various dietary patterns and anthropometric parameters except dietary pattern one (salty snacks, regular soft drinks, milk, sweetened yogurt, ice cream, and cooked vegetables), which had a positive correlation with weight (p=0.002) and BMI (p=0.038). PUD patients should target weight reduction actions and reduce alcohol intake as measures to control the recurrence of the disease. Nutrition Education among this population must be promoted to minimize the recurrence of PUD.

Keywords: Dietary patterns, lifestyle factors, nutritional status, peptic ulcer disease

Procedia PDF Downloads 50

Authors: Masahiro Takimoto

Abstract:

The present study explored how the metaphor awareness-raising approach affects the involvement of the right hemisphere in developing EFL learners’ knowledge regarding the different degrees of politeness embedded within different request expressions. The present study was motivated by theoretical considerations regarding the conceptual projection and the metaphorical idea of politeness is distance, as proposed; this study applied these considerations to develop Japanese learners’ knowledge regarding the different politeness degrees and to explore the connection between the metaphorical concept projection and right-hemisphere dominance. Japanese EFL learners do not know certain language strategies (e.g., English requests can be mitigated with biclausal downgraders, including the if-clause with past-tense modal verbs) and have difficulty adjusting the politeness degrees attached to request expressions according to situations. The present study used a pre/post-test design to reaffirm the efficacy of the cognitive technique and its connection to right-hemisphere involvement by mouth asymmetry technique. Mouth asymmetry measurement has been utilized because speech articulation, normally controlled mainly by one side of the brain, causes muscles on the opposite side of the mouth to move more during speech production. The present research did not administer the delayed post-test because it emphasized determining whether metaphor awareness-raising approaches for developing EFL learners’ pragmatic proficiency entailed right-hemisphere activation. Each test contained an acceptability judgment test (AJT) along with a speaking test in the post-test. The study results show that the metaphor awareness-raising group performed significantly better than the control group with regard to acceptability judgment and speaking tests post-test. These data revealed that the metaphor awareness-raising approach could promote L2 learning because it aided input enhancement and concept projection; through these aspects, the participants were able to comprehend an abstract concept: the degree of politeness in terms of the spatial concept of distance. Accordingly, the proximal-distal metaphor enabled the study participants to connect the newly spatio-visualized concept of distance to the different politeness degrees attached to different request expressions; furthermore, they could recall them with the left side of the mouth being wider than the right. This supported certain findings from previous studies that indicated the possible involvement of the brain's right hemisphere in metaphor processing.

Keywords: metaphor awareness-raising, right hemisphere, L2 politeness, mouth asymmetry

Procedia PDF Downloads 119

Authors: Gwendolyn Royal-Smith

Abstract:

Cocaine ranks as one of the world’s most addictive and commonly abused stimulant drugs. Recent evidence indicates that the abuse of cocaine has risen so quickly among females that this group now accounts for about 40 percent of all users in the United States. Neuropsychological studies have demonstrated that specific neural activation patterns carry higher risks for neurocognitive and executive function in cocaine addicted females thereby increasing their vulnerability for poorer treatment outcomes and more frequent post-treatment relapse when compared to males. This study examined secondary data with a convenience sample of 164 cocaine addicted male and females to assess neurocognitive and executive function. The principal objective of this study was to assess whether individual performance on the Stroop Word Color Task is predictive of treatment success by gender. A second objective of the study evaluated whether individual performance employing neurocognitive measures including the Stroop Word-Color task, the Rey Auditory Verbal Learning Test (RALVT), the Iowa Gambling Task, the Wisconsin Card Sorting Task (WISCT), the total score from the Barratte Impulsiveness Scale (Version 11) (BIS-11) and the total score from the Frontal Systems Behavioral Scale (FrSBE) test demonstrated differences in neurocognitive and executive function performance by gender. Logistic regression models were employed utilizing a covariate adjusted model application. Initial analyses of the Stroop Word color tasks indicated significant differences in the performance of males and females, with females experiencing more challenges in derived interference reaction time and associate recall ability. In early testing including the Rey Auditory Verbal Learning Test (RALVT), the number of advantageous vs disadvantageous cards from the Iowa Gambling Task, the number of perseverance errors from the Wisconsin Card Sorting Task (WISCT), the total score from the Barratte Impulsiveness Scale (Version 11) (BIS-11) and the total score from the Frontal Systems Behavioral Scale, results were mixed with women scoring lower in multiple indicators in both neurocognitive and executive function.

Keywords: cocaine addiction, gender, neuropsychology, neurocognitive, executive function

Procedia PDF Downloads 375

Authors: Kumar Shashvat, Amol P. Bhondekar

Abstract:

In the midst of the five senses, odor is the most reminiscent and least understood. Odor testing has been mysterious and odor data fabled to most practitioners. The delinquent of recognition and classification of odor is important to achieve. The facility to smell and predict whether the artifact is of further use or it has become undesirable for consumption; the imitation of this problem hooked on a model is of consideration. The general industrial standard for this classification is color based anyhow; odor can be improved classifier than color based classification and if incorporated in machine will be awfully constructive. For cataloging of odor for peas, trees and cashews various discriminative approaches have been used Discriminative approaches offer good prognostic performance and have been widely used in many applications but are incapable to make effectual use of the unlabeled information. In such scenarios, generative approaches have better applicability, as they are able to knob glitches, such as in set-ups where variability in the series of possible input vectors is enormous. Generative models are integrated in machine learning for either modeling data directly or as a transitional step to form an indeterminate probability density function. The algorithms or models Linear Discriminant Analysis and Naive Bayes Classifier have been used for classification of the odor of cashews. Linear Discriminant Analysis is a method used in data classification, pattern recognition, and machine learning to discover a linear combination of features that typifies or divides two or more classes of objects or procedures. The Naive Bayes algorithm is a classification approach base on Bayes rule and a set of qualified independence theory. Naive Bayes classifiers are highly scalable, requiring a number of restraints linear in the number of variables (features/predictors) in a learning predicament. The main recompenses of using the generative models are generally a Generative Models make stronger assumptions about the data, specifically, about the distribution of predictors given the response variables. The Electronic instrument which is used for artificial odor sensing and classification is an electronic nose. This device is designed to imitate the anthropological sense of odor by providing an analysis of individual chemicals or chemical mixtures. The experimental results have been evaluated in the form of the performance measures i.e. are accuracy, precision and recall. The investigational results have proven that the overall performance of the Linear Discriminant Analysis was better in assessment to the Naive Bayes Classifier on cashew dataset.

Keywords: odor classification, generative models, naive bayes, linear discriminant analysis

Procedia PDF Downloads 353

Authors: Mariamawit T. Belete

Abstract:

Cereal production and marketing are the means of livelihood for millions of households in Ethiopia. However, cereal production is constrained by technical and socio-economic factors. Among the technical factors, cereal crop diseases are the major contributing factors to the low yield. The aim of this research is to develop an integration of data mining and knowledge based system for sorghum anthracnose disease diagnosis that assists agriculture experts and development agents to make timely decisions. Anthracnose diagnosing systems gather information from Melkassa agricultural research center and attempt to score anthracnose severity scale. Empirical research is designed for data exploration, modeling, and confirmatory procedures for testing hypothesis and prediction to draw a sound conclusion. WEKA (Waikato Environment for Knowledge Analysis) was employed for the modeling. Knowledge based system has come across a variety of approaches based on the knowledge representation method; case-based reasoning (CBR) is one of the popular approaches used in knowledge-based system. CBR is a problem solving strategy that uses previous cases to solve new problems. The system utilizes hidden knowledge extracted by employing clustering algorithms, specifically K-means clustering from sampled anthracnose dataset. Clustered cases with centroid value are mapped to jCOLIBRI, and then the integrator application is created using NetBeans with JDK 8.0.2. The important part of a case based reasoning model includes case retrieval; the similarity measuring stage, reuse; which allows domain expert to transfer retrieval case solution to suit for the current case, revise; to test the solution, and retain to store the confirmed solution to the case base for future use. Evaluation of the system was done for both system performance and user acceptance. For testing the prototype, seven test cases were used. Experimental result shows that the system achieves an average precision and recall values of 70% and 83%, respectively. User acceptance testing also performed by involving five domain experts, and an average of 83% acceptance is achieved. Although the result of this study is promising, however, further study should be done an investigation on hybrid approach such as rule based reasoning, and pictorial retrieval process are recommended.

Keywords: sorghum anthracnose, data mining, case based reasoning, integration

Procedia PDF Downloads 59

Authors: Najeh Lakhoua

Abstract:

Introduction: Scientific developments and techniques for the systemic approach generate several names to the systemic approach: systems analysis, systems analysis, structural analysis. The main purpose of these reflections is to find a multi-disciplinary approach which organizes knowledge, creates universal language design and controls complex sets. In fact, system analysis is structured sequentially by steps: the observation of the system by various observers in various aspects, the analysis of interactions and regulatory chains, the modeling that takes into account the evolution of the system, the simulation and the real tests in order to obtain the consensus. Thus the system approach allows two types of analysis according to the structure and the function of the system. The purpose of this paper is to present an application of system analysis of Unmanned Aerial Vehicle (UAV) components in order to represent the architecture of this system. Method: There are various analysis methods which are proposed, in the literature, in to carry out actions of global analysis and different points of view as SADT method (Structured Analysis and Design Technique), Petri Network. The methodology adopted in order to contribute to the system analysis of an Unmanned Aerial Vehicle has been proposed in this paper and it is based on the use of SADT. In fact, we present a functional analysis based on the SADT method of UAV components Body, power supply and platform, computing, sensors, actuators, software, loop principles, flight controls and communications). Results: In this part, we present the application of SADT method for the functional analysis of the UAV components. This SADT model will be composed exclusively of actigrams. It starts with the main function ‘To analysis of the UAV components’. Then, this function is broken into sub-functions and this process is developed until the last decomposition level has been reached (levels A1, A2, A3 and A4). Recall that SADT techniques are semi-formal; however, for the same subject, different correct models can be built without having to know with certitude which model is the good or, at least, the best. In fact, this kind of model allows users a sufficient freedom in its construction and so the subjective factor introduces a supplementary dimension for its validation. That is why the validation step on the whole necessitates the confrontation of different points of views. Conclusion: In this paper, we presented an application of system analysis of Unmanned Aerial Vehicle components. In fact, this application of system analysis is based on SADT method (Structured Analysis Design Technique). This functional analysis proved the useful use of SADT method and its ability of describing complex dynamic systems.

Keywords: system analysis, unmanned aerial vehicle, functional analysis, architecture

Procedia PDF Downloads 167

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 74

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 26

Authors: S. Fazelifar, M. Ghasemi

Abstract:

Aim: Recent studies on cardiovascular risk factors have been focused on the new markers of inflammatory diseases such as C-reactive protein (CRP). Research evidence shows that physical activity along with other factors such as reduced smoking, controlling blood pressure, control blood lipids TC, LDL-c, HDL-c and having a healthy weight can reduce the risk of chronic heart disease (CHD) .Therefore, the aim of this study was to determine the effect of twelve weeks aerobic exercise and consumption of apple vinegar on cardiovascular risk factor in older women. Methodology: 28 inactive women (mean body weight 72.13 ± 8.6 kg, height 157 ± 7.4cm, age 48.06 ± 5.18 years and BMI 28.2 ± 3.2 kg/m2) by recall and notice of investigation, among of the eligible voters recruited and randomly divided in 4 groups: control, apple vinegar, exercise, exercise + apple vinegar. The training program includes a 20-minute warm-up and stretching, running for 15 minutes in the first session with an intensity of 80% of maximum heart rate and an increase in one-minute run time in next training session. Also, subjects in experimental groups received daily specified amount of 50 ml apple vinegar. Blood samples were collected from the brachial vein in before and after training to measure CRP and blood lipids (cholesterol, HDL, VLDL, LDL). The levels of CRP were measured by ELISA way. K-S test to determine the normality of the data and analysis of variance for repeated measures was used to analyze the data. A significant difference in the p < 0/05 accepted. Results: The results indicated that individual characteristics including height, weight, age, and body mass index were not significantly different among the four groups. The results showed that levels of CRP and LDL cholesterol were significantly reduced in all groups at post-test compared to the pre-test. The HDL levels increased significantly in all groups in post-test compared to the pre-test. Analysis of the data indicates that levels of CRP, TC, and LDL were significantly reduced in all groups compared to the control group, while the changes in the other groups were not significant relative to each other. Conclusion: Results of this study showed that twelve weeks of aerobic exercise with apple vinegar cause a significant decrease in CRP, cholesterol, LDL, and significantly increased HDL levels. According to the results of this study, it is possible that aerobic exercise with apple vinegar can inhibit CRP and undesirable fats. Considering the strong association between the inflammatory indices and the prevalence of cardiovascular diseases, every factor that decreases these indices can reduce the cardiovascular complications.

Keywords: aerobic exercise, apple vinegar, CRP, older women

Procedia PDF Downloads 426

Authors: Meiying Liao, Poya Huang

Abstract:

The aesthetic domain is one of the six major domains in the Taiwanese preschool curriculum, encompassing visual arts, music, and dramatic play. Its primary objective is to cultivate children’s abilities in exploration and awareness, expression and creation, and response and appreciation. The purpose of this study was to explore the effects of hosting a vocal music concert on aesthetic inspiration and learning among preschoolers in a preschool setting. The primary research method employed was a case study focusing on a private preschool in Northern Taiwan that organized a school-wide event featuring two vocalists. The concert repertoires included children’s songs, folk songs, and arias performed in Mandarin, Hakka, English, German, and Italian. In addition to professional performances, preschool teachers actively participated by presenting a children’s song. A total of 5 classes, comprising approximately 150 preschoolers, along with 16 teachers and staff, participated in the event. Data collection methods included observation, interviews, and documents. Results indicated that both teachers and children thoroughly enjoyed the concert, with high levels of acceptance when the program was appropriately designed and hosted. Teachers reported that post-concert discussions with children revealed the latter’s ability to recall people, events, and elements observed during the performance, expressing their impressions of the most memorable segments. The concert effectively achieved the goals of the aesthetic domain, particularly in fostering response and appreciation. It also inspired preschoolers’ interest in music. Many teachers noted an increased desire for performance among preschoolers after exposure to the concert, with children imitating the performers and their expressions. Remarkably, one class extended this experience by incorporating it into the curriculum, autonomously organizing a high-quality concert in the music learning center. Parents also reported that preschoolers enthusiastically shared their concert experiences at home. In conclusion, despite being a single event, the positive responses from preschoolers towards the music performance suggest a meaningful impact. These experiences extended into the curriculum, as firsthand exposure to performances allowed teachers to deepen related topics, fostering a habit of autonomous learning in the designated learning centers.

Keywords: concert, early childhood music education, aesthetic education, music develpment

Procedia PDF Downloads 20