Search results for: Adult dataset

Authors: Grace D. Severo, Lopita U. Jung

Abstract:

This study aimed to determine the educational philosophies and teaching styles of the college faculty of the University of Perpetual Help System DALTA in the campuses of Las-Piñas, Molino, and Calamba, south of Metro Manila. It sought to determine the relationships of educational philosophy and teaching styles of the college faculty vis-à-vis the university system’s educational philosophies and teaching style preferences. A hundred and five faculty members from the Colleges of Education, Arts and Sciences responded to the survey during the academic year 2014-2015. The Philosophy of Adult Education Inventory measured the faculty’s preferred educational philosophies. The Principles of Adult Learning Scale measured the faculty’s teaching style preference. Findings show that there is a similarity between the university system and the faculty members in using the progressive educational philosophy, however both contrasted in the preferred teaching style. Majority of the faculty held progressive educational philosophy but their preference for teacher-centered teaching style did not match. This implies that the majority are certain of having progressive educational philosophy but are not utilizing the learner-centered teaching styles; a high degree of support and commitment to practice a progressive and humanist philosophical orientation in education; and a high degree of support on teacher-centered teaching style promotion from the institution can strengthen a high degree of commitment for the faculty to enunciate their values and practice through these educational philosophies and teaching styles.

Keywords: educational philosophies, teaching styles, philosophy of adult education inventory, principles of adult learning scale

Procedia PDF Downloads 367

Authors: Mo-Se Lee, Cheol-Hwi Ahn, Kee-Young Kwahk, Hyunchul Ahn

Abstract:

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN (Convolutional Neural Network), which is known as effective solution for recognizing and classifying images, has been popularly applied to classification and prediction problems in various fields. In this study, we try to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. In specific, we propose to apply CNN as the binary classifier that predicts stock market direction (up or down) by using a graph as its input. That is, our proposal is to build a machine learning algorithm that mimics a person who looks at the graph and predicts whether the trend will go up or down. Our proposed model consists of four steps. In the first step, it divides the dataset into 5 days, 10 days, 15 days, and 20 days. And then, it creates graphs for each interval in step 2. In the next step, CNN classifiers are trained using the graphs generated in the previous step. In step 4, it optimizes the hyper parameters of the trained model by using the validation dataset. To validate our model, we will apply it to the prediction of KOSPI200 for 1,986 days in eight years (from 2009 to 2016). The experimental dataset will include 14 technical indicators such as CCI, Momentum, ROC and daily closing price of KOSPI200 of Korean stock market.

Keywords: convolutional neural network, deep learning, Korean stock market, stock market prediction

Procedia PDF Downloads 425

Authors: Jayanti Pujari

Abstract:

The present study attempts to find out the barriers faced by adult women with an Intellectual disability during their training at vocational training centres offered by rehabilitation institutes. As economic independence is the ultimate aim of rehabilitation, this study tries to focus on the barriers which restrict the adult women with intellectual disability in equipping themselves in required skill which can really empower them and help them in independent living. The objectives of the study are (1) To find out the barriers perceived by job coaches during training given to women with intellectual disability (2) To find out the barriers perceived by the parents of women with intellectual disability who are undergoing vocational training and (3) To find out the barriers perceived by the women with intellectual disabilities during the vocational training. The barriers have been operationalised in the present study from three perspectives such as behavioural barriers, competency related barriers and accessibility barriers. For the present study three groups of participants(N=60) have been selected through purposive nonprobability sampling procedure to generate the data. They are( 20) job coaches who are working at vocational centres, (20) parents of women with intellectual disabilities, (20) adult women with intellectual disabilities. The study followed a descriptive research design and data are generated through self developed questionnaire. Three sets of self-developed and face validated questionnaires were used as the tool to gather the data from the three categories of sample. The questionnaire has 30 close ended questions and the respondents have to answer on a three point scale (yes, no, need help). Both qualitative and quantitative analysis was conducted to test the hypothesis. The major findings of the study depict that the 87% of the women with intellectual disability perceived highest barriers related to competency whereas barriers related to behaviour and accessibility are perceived lowest. 92% of job coaches perceived barriers related to competencies and accessibility are highest which hinder the effectiveness of skill development of women with intellectual disability and 74% of the parents of adult women with intellectual disability also opines that the barriers related to competencies and accessibility are highest. In conclusion, it is stressed that there is need to create awareness among the stakeholders about the training and management strategies of skill training and positive behaviour support which will surely enable the adult women with intellectual disability to utilise their residual skill and acquire training to become economically independent.

Keywords: economic independence, intellectual disability, skill development, training barrier

Procedia PDF Downloads 223

Authors: Kemal Polat

Abstract:

In this study, it has been estimated whether there is skin by using RBG values obtained from the camera and k-nearest neighbor (k-NN) classifier. The dataset used in this study has an unbalanced distribution and a linearly non-separable structure. This problem can also be called a big data problem. The Skin dataset was taken from UCI machine learning repository. As the classifier, we have used the k-NN method to handle this big data problem. For k value of k-NN classifier, we have used as 1. To train and test the k-NN classifier, 50-50% training-testing partition has been used. As the performance metrics, TP rate, FP Rate, Precision, recall, f-measure and AUC values have been used to evaluate the performance of k-NN classifier. These obtained results are as follows: 0.999, 0.001, 0.999, 0.999, 0.999, and 1,00. As can be seen from the obtained results, this proposed method could be used to predict whether the image is skin or not.

Keywords: k-NN classifier, skin or non-skin classification, RGB values, classification

Procedia PDF Downloads 248

Authors: Csaba Kalman

Abstract:

In spite of the existence of numerous second language (L2) motivation theories, the teacher’s role in motivating learners has remained an under-researched niche to this day. If we narrow down our focus on the teacher’s role on motivating adult learners of English in an English as a Foreign Language (EFL) context in corporate environments, empirical research is practically non-existent. This study fills the above research niche by exploring the most motivating aspects of the teacher’s personality, behaviour, and teaching practices that affect adult learners’ L2 motivation in corporate contexts in Hungary. The study was conducted in a wide range of industries in 18 organisations that employ over 250 people in Hungary. In order to triangulate the research, 21 human resources managers, 18 language teachers, and 466 adult learners of English were involved in the investigation by participating in interview studies, and quantitative questionnaire studies that measured ten scales related to the teacher’s role, as well as two criterion measure scales of intrinsic and extrinsic motivation. The qualitative data were analysed using a template organising style, while descriptive, inferential statistics, as well as multivariate statistical techniques, such as correlation and regression analyses, were used for analysing the quantitative data. The results showed that certain aspects of the teacher’s personality (thoroughness, enthusiasm, credibility, and flexibility), as well as preparedness, incorporating English for Specific Purposes (ESP) in the syllabus, and focusing on the present, proved to be the most salient aspects of the teacher’s motivating influence. The regression analyses conducted with the criterion measure scales revealed that 22% of the variance in learners’ intrinsic motivation could be explained by the teacher’s preparedness and appearance, and 23% of the variance in learners’ extrinsic motivation could be attributed to the teacher’s personal branding and incorporating ESP in the syllabus. The findings confirm the pivotal role teachers play in motivating L2 learners independent of the context they teach in; and, at the same time, call for further research so that we can better conceptualise the motivating influence of L2 teachers.

Keywords: adult learners, corporate contexts, motivation, teacher’s role

Procedia PDF Downloads 104

Authors: Gurukiran Veerapur, Nytik Birudavolu, Seetharam U. N., Chandravva Hebbi, R. Praneeth Reddy

Abstract:

This work presents a robust approach for the recognition of characters in Telugu and Kannada, two South Indian scripts with structural similarities in characters. To recognize the characters exhaustive datasets are required, but there are only a few publicly available datasets. As a result, we decided to create a dataset for one language (source language),train the model with it, and then test it with the target language.Telugu is the target language in this work, whereas Kannada is the source language. The suggested method makes use of Canny edge features to increase character identification accuracy on pictures with noise and different lighting. A dataset of 45,150 images containing printed Kannada characters was created. The Nudi software was used to automatically generate printed Kannada characters with different writing styles and variations. Manual labelling was employed to ensure the accuracy of the character labels. The deep learning models like CNN (Convolutional Neural Network) and Visual Attention neural network (VAN) are used to experiment with the dataset. A Visual Attention neural network (VAN) architecture was adopted, incorporating additional channels for Canny edge features as the results obtained were good with this approach. The model's accuracy on the combined Telugu and Kannada test dataset was an outstanding 97.3%. Performance was better with Canny edge characteristics applied than with a model that solely used the original grayscale images. The accuracy of the model was found to be 80.11% for Telugu characters and 98.01% for Kannada words when it was tested with these languages. This model, which makes use of cutting-edge machine learning techniques, shows excellent accuracy when identifying and categorizing characters from these scripts.

Keywords: base characters, modifiers, guninthalu, aksharas, vattakshara, VAN

Procedia PDF Downloads 53

Authors: Banaz Sdiq Abdulla

Abstract:

Four local species (Allium sativum, Capsicum annum, Anethum graveolens, and Ocimum basilicum) were evaluated in the laboratory of Biolog Department, College of Education, for their ability to protect stored rice from the infection by weevil Sitophilus oryzae. Aqueous extracts of the plant species were applied as direct admixture of three concentrations levels of 1%, 2.5%, and 5% (W/V) to assess for mortality, adult emergence, and repellency and weight losses. The results showed that Al. sativum extracts was the most effective as it gave the highest mortality (90%)at 5% concentration followed by Capsicum annum (80%) on the 4th day post treatment, the result showed that the plant extract of different concentrations exhibited different level of reduction in adult emergence and different repellency of adults of Sitophilus oryzae. Allium sativum recorded the lowest mean number of adult emergence (8) followed by Capsicum annum (10) at 5% concentration, while Capsicum annum was found to be revealed complete repellent agent (100%) repellency on the 6th hours against Sitophilus oryzae followed by Allium sativum and Anethum graveolens (81.8%). There was a significant (P>0.05) reduction in the weight lossed by the weevils with less damaged recorded on grain treated with Allium sativum and Capsicum annum (1.6%) and (2.3%) respectively.

Keywords: plant extraction, rice, protectant, pest

Procedia PDF Downloads 431

Authors: Anna Ching-Yu Wong

Abstract:

This study aims to identify the quality and effectiveness of the adult programs provided by the public library using the ServQUAL Method and the National Library Public Programs Assessment guidelines (NIPPA, June 2019). ServQUAl covers several variables, namely: tangible, reliability, responsiveness, assurance, and empathy. NIPPA guidelines focus on program characteristics, particularly on the outcomes – the level of satisfaction from program participants. The reached populations were adults who participated in library adult programs at a small-town public library in Kansas. This study was designed as quantitative evaluative research which analyzed the quality and effectiveness of the library adult programs by analyzing the role of each factor based on ServQUAL and the NIPPA's library program assessment guidelines. Data were collected from November 2019 to January 2020 using a questionnaire with a Likert Scale. The data obtained were analyzed in a descriptive quantitative manner. The impact of this research can provide information about the quality and effectiveness of existing programs and can be used as input to develop strategies for developing future adult programs. Overall the result of ServQUAL measurement is in very good quality, but still, areas need improvement and emphasis in each variable: Tangible Variables still need improvement in indicators of the temperature and space of the meeting room. Reliability Variable still needs improvement in the timely delivery of the programs. Responsiveness Variable still needs improvement in terms of the ability of the presenters to convey trust and confidence from participants. Assurance Variables still need improvement in the indicator of knowledge and skills of program presenters. Empathy Variable still needs improvement in terms of the presenters' willingness to provide extra assistance. The result of program outcomes measurement based on NIPPA guidelines is very positive. Over 96% of participants indicated that the programs were informative and fun. They learned new knowledge and new skills and would recommend the programs to their friends and families. They believed that together, the library and participants build stronger and healthier communities.

Keywords: ServQual model, ServQual in public libraries, library program assessment, NIPPA library programs assessment

Procedia PDF Downloads 95

Authors: Hangsik Shin

Abstract:

The purpose of this research is to restore the feature location of under-sampled photoplethysmogram using spline interpolation and to investigate feasibility for feature shape restoration. We obtained 10 kHz-sampled photoplethysmogram and decimated it to generate under-sampled dataset. Decimated dataset has 5 kHz, 2.5 k Hz, 1 kHz, 500 Hz, 250 Hz, 25 Hz and 10 Hz sampling frequency. To investigate the restoration performance, we interpolated under-sampled signals with 10 kHz, then compared feature locations with feature locations of 10 kHz sampled photoplethysmogram. Features were upper and lower peak of photplethysmography waveform. Result showed that time differences were dramatically decreased by interpolation. Location error was lesser than 1 ms in both feature types. In 10 Hz sampled cases, location error was also deceased a lot, however, they were still over 10 ms.

Keywords: peak detection, photoplethysmography, sampling, signal reconstruction

Procedia PDF Downloads 368

Authors: Basma Khelfa, Antoine Tordeux, Ibrahima Ba

Abstract:

We present a descriptive analysis data of lane-changing events in multi-lane roads. The data are provided from The Highway Drone Dataset (HighD), which are microscopic trajectories in highway. This paper describes and analyses the role of the different parameters and their significance. Thanks to HighD data, we aim to find the most frequent reasons that motivate drivers to change lanes. We used the programming language R for the processing of these data. We analyze the involvement and relationship of different variables of each parameter of the ego vehicle and the four vehicles surrounding it, i.e., distance, speed difference, time gap, and acceleration. This was studied according to the class of the vehicle (car or truck), and according to the maneuver it undertook (overtaking or falling back).

Keywords: autonomous driving, physical traffic model, prediction model, statistical learning process

Procedia PDF Downloads 261

Authors: Tamanna Jethava, Rahul Joshi

Abstract:

Frequent Item sets play an essential role in many data Mining tasks that try to find interesting patterns from the database. Typically it refers to a set of items that frequently appear together in transaction dataset. There are several mining algorithm being used for frequent item set mining, yet most do not scale to the type of data we presented with today, so called “BIG DATA”. Big Data is a collection of large data sets. Our approach is to work on the frequent item set mining over the large dataset with scalable and speedy way. Big Data basically works with Map Reduce along with HDFS is used to find out frequent item sets from Big Data on large cluster. This paper focuses on using pre-processing & mining algorithm as hybrid approach for big data over Hadoop platform.

Keywords: frequent item set mining, big data, Hadoop, MapReduce

Procedia PDF Downloads 435

Authors: Mohammad Narimani, Zahra Rostamoghli

Abstract:

The main objective of this study is the survey of rate and causes of literacy preservation in adult newly learners. Statistical sample consists of 384 adults who are newly learners of literacy, at 2002, who were selected by stratified sampling method. This is a correlation cross-sectional survey research, in which authors-constructed measures were used for data collection. Results of survey showed that learners' literacy preservation rate after two years was 70%, 61% and 57%, in reading, dictation and mathematic tests, respectively.Following can be noted as factors correlated with literacy preservation; repetition of subjects and learners' subjective review, access to and using the library and publications, feeling of need to and interest in educated matters, socio cultural class of learners, and literacy level of learners' family.

Keywords: literacy preservation, new learner, literacy improvement movement, mathematic test

Procedia PDF Downloads 478

Authors: Mehravar Javid, Sadrieh Khajavi Mazanderani, Kelly Gleischman, Zoe Andris

Abstract:

The present study was conducted with the aim of investigating the effectiveness of transactional analysis group training on self-knowledge and Its dimensions (self, child, and adult) in counselors working in public and private high schools in Tehran. Counseling has become an important job for society, and there is a need for consultants in organizations. Providing better and more efficient counseling is one of the goals of the education system. The personal characteristics of counselors are important for the success of the therapy. In TA, humans have three ego states, which are named parent, adult, and child, and the main concept in the transactional analysis is self-state, which means a stable feeling and pattern of thinking related to behavioral patterns. Self-knowledge, considered a prerequisite to effective communication, fosters psychological growth, and recognizing it, is pivotal for emotional development, leading to profound insights. The research sample included 30 working counselors (22 women and 8 men) in the academic year 2019-2020 who achieved the lowest scores on the self-knowledge questionnaire. The research method was quasi-experimental with a control group (15 people in the experimental group and 15 people in the control group). The research tool was a self-awareness questionnaire with 29 questions and three subscales (child, parent, and adult Ego state). The experimental group was exposed to transactional analysis training for 10 once-weekly 2-hour sessions; the questionnaire was implemented in both groups (post-test). Multivariate covariance analysis was used to analyze the data. The data showed that the level of self-awareness of counselors who received transactional analysis training is higher than that of counselors who did not receive any training (p<0.01). The result obtained from this analysis shows that transactional analysis training is an effective therapy for enhancing self-knowledge and its subscales (Adult ego state, Parent ego state, and Child ego state). Teaching transactional analysis increases self-knowledge, and self-realization and helps people to achieve independence and remove irresponsibility to improve intra-personal and interpersonal relationships.

Keywords: ego state, group, transactional analysis, self-knowledge

Procedia PDF Downloads 75

Authors: Waheed Anwar, Kiran Nawaz, Muhammad Saleem Haider, Ahmad Ali Shahid, Sehrish Iftikhar

Abstract:

The whitefly, Bemisia tabaci (Gennadius), is a complex insect species, including many cryptic species or biotypes. Whitefly causes damage to many ornamental and horticultural crops through directly feeding on phloem sap, resulting in sooty mould and critically decreases the rate of photosynthesis of many host plants. Biological control has emerged as one of the most important methods for the management of soil-borne plant pathogens. Among the natural enemies of insects different entomopathogenic fungi are mostly used as biological control of the pest. The purpose of this research was to find indigenous insect-associated fungi and their virulence against Bemisia tabaci. A detailed survey of cotton fields in sample collection was conducted during July and August 2013 from the central mixed zone of Punjab, Pakistan. For the isolation of T. longibrachiatum, sabouraud dextrose peptone yeast extract agar (SDAY) media was used and morphological characterization of isolated T. longibrachiatum was studied using different dichotomous keys. Molecular Identification of the pathogen was confirmed by amplifying the internal transcribed spacer region. Blastn analysis showed 100% homology with already reported sequences on the database. For these bioassays, two conidial concentrations 4 × 108/mL & 4 × 104/mL of T. longibrachiatum was sprayed in clip cages for nymph and adult B. tabaci respectively under controlled environmental conditions. The pathogenicity of T. longibrachiatum was tested on nymph and adult whitefly to check mortality. Mortality of B. tabaci at nymphal and adult stages were observed after 24-hour intervals. Percentage mortality of nymphs treated with 4 x 104/mL conidia of T. longibrachiatum was 20, 24, 36 and 40% after 48, 72, 96, 72, 96, 120 and 144 hours respectively. However, no considerable difference was recorded in percentage mortality of whitefly after 120 and 144 hours. There were great variations after 24, 48, 72 and 96 hours in the rate of mortality. The efficacy of T. longibrachiatum as entomopathogenic fungi was evaluated in adult and nymphal stages of whitefly. Trichoderma longibrachiatum showed maximum activity on nymphal stages of whitefly as compared to adult stages. The percentage of conidial germination was also recorded on the outer surface of adult and nymphal stages of B. tabaci. The present findings indicated that T. longibrachiatum is an entomopathogenic fungus against B. tabaci and many species of Trichoderma were already reported as an antagonistc organism against a wide range of bacterial and fungal pathogens.

Keywords: efficacy, Trichoderma, virulence, bioassay

Procedia PDF Downloads 287

Authors: Oluwaponmile David Alao

Abstract:

Misdiagnosis has been the major problem in health sector. Heart attack has been one of diseases that have high level of misdiagnosis recorded on the part of physicians. In this paper, an intelligent system has been developed for diagnosis of heart attack in the health sector. Dataset of heart attack obtained from UCI repository has been used. This dataset is made up of thirteen attributes which are very vital in diagnosis of heart disease. The system is developed on the multilayer perceptron trained with back propagation neural network then simulated with feed forward neural network and a recognition rate of 87% was obtained which is a good result for diagnosis of heart attack in medical field.

Keywords: heart attack, artificial neural network, diagnosis, intelligent system

Procedia PDF Downloads 655

Authors: V. Surena, B. Nazemisalman, F. Noghrehkar

Abstract:

Introduction: Gingival overgrowth (GO) is a common side effect involving users of antiepileptic, immunosuppressive and calcium channel blocker drugs. Cyclosporine and phenytoin are amongst the most widely used drugs associated with GO. Gingival fibroblasts seem to have a significant role in the production of certain enzymes after administration of the drugs contributing to GO. Previous studies have shown a higher prevalence of GO in children and adolescents. The aim of this study was to compare normal human gingival fibroblasts with those exposed to Cyclosporine or phenytoin in measuring the production levels of certain enzymes that could have a possible role in GO. Methods: samples were obtained from the gingival biopsies of seven adult and seven children and were cultured into plates. With the growth of fibroblast cells, they were treated with or without either Cyclosporine or phenytoin. Reverse transcriptase-polymerase chain reaction (RT-PCR) was used to determine the expressed levels of R-EGF, cathepsin B,L, Lysyl oxidase, COL1, TGF β1, MMP-1,2, and TIMP1. Results: according to RT-PCR analyses, the expressed levels of R-EGF, cathepsin B, L, Lysyl oxidase, COL1, TGF β1, MMP-1, 2 and TIMP1 were affected by Cyclosporine and phenytoin. TGF-β1, TIMP, Cathepsin B and EGF showed comparable values in the adult and pediatric groups. Conclusions: Different expressed levels of enzymes after treatment of the gingival fibroblasts of adults and pediatrics with phenytoin or Cyclosporine could be the reason for the higher severity of GO in children. More studies need to be performed on the pathogenesis of GO at different age groups.

Keywords: cyclosporine, fibroblasts, phenytoin, gingivae

Procedia PDF Downloads 270

Authors: Tetsuro Saeki, Yuichi Kato, Shoutarou Mizuno

Abstract:

STRIM (Statistical Test Rule Induction Method) has been proposed as a method to effectively induct if-then rules from the decision table which is considered as a sample set obtained from the population of interest. Its usefulness has been confirmed by simulation experiments specifying rules in advance, and by comparison with conventional methods. However, scope for future development remains before STRIM can be applied to the analysis of real-world data sets. The first requirement is to determine the size of the dataset needed for inducting true rules, since finding statistically significant rules is the core of the method. The second is to examine the capacity of rule induction from datasets with contaminated attribute values created by missing data and noise, since real-world datasets usually contain such contaminated data. This paper examines the first problem theoretically, in connection with the rule length. The second problem is then examined in a simulation experiment, utilizing the critical size of dataset derived from the first step. The experimental results show that STRIM is highly robust in the analysis of datasets with contaminated attribute values, and hence is applicable to realworld data.

Keywords: rule induction, decision table, missing data, noise

Procedia PDF Downloads 396

Authors: Vo Ngoc Phu, Phan Thi Tuoi

Abstract:

We have explored different methods of improving the accuracy of sentiment classification. The sentiment orientation of a document can be positive (+), negative (-), or neutral (0). We combine five dictionaries from [2, 3, 4, 5, 6] into the new one with 21137 entries. The new dictionary has many verbs, adverbs, phrases and idioms, that are not in five ones before. The paper shows that our proposed method based on the combination of Term-Counting method and Enhanced Contextual Valence Shifters method has improved the accuracy of sentiment classification. The combined method has accuracy 68.984% on the testing dataset, and 69.224% on the training dataset. All of these methods are implemented to classify the reviews based on our new dictionary and the Internet Movie data set.

Keywords: sentiment classification, sentiment orientation, valence shifters, contextual, valence shifters, term counting

Procedia PDF Downloads 503

Authors: Rosa Figueroa, Christopher Flores

Abstract:

Text categorization is the problem of assigning a new document to a set of predetermined categories, on the basis of a training set of free-text data that contains documents whose category membership is known. To train a classification model, it is necessary to extract characteristics in the form of tokens that facilitate the learning and classification process. In text categorization, the feature extraction process involves the use of word sequences also known as N-grams. In general, it is expected that documents belonging to the same category share similar features. The Smith-Waterman (SW) algorithm is a dynamic programming algorithm that performs a local sequence alignment in order to determine similar regions between two strings or protein sequences. This work explores the use of SW algorithm as an alternative to feature extraction in text categorization. The dataset used for this purpose, contains 2,610 annotated documents with the classes Obese/Non-Obese. This dataset was represented in a matrix form using the Bag of Word approach. The score selected to represent the occurrence of the tokens in each document was the term frequency-inverse document frequency (TF-IDF). In order to extract features for classification, four experiments were conducted: the first experiment used SW to extract features, the second one used unigrams (single word), the third one used bigrams (two word sequence) and the last experiment used a combination of unigrams and bigrams to extract features for classification. To test the effectiveness of the extracted feature set for the four experiments, a Support Vector Machine (SVM) classifier was tuned using 20% of the dataset. The remaining 80% of the dataset together with 5-Fold Cross Validation were used to evaluate and compare the performance of the four experiments of feature extraction. Results from the tuning process suggest that SW performs better than the N-gram based feature extraction. These results were confirmed by using the remaining 80% of the dataset, where SW performed the best (accuracy = 97.10%, weighted average F-measure = 97.07%). The second best was obtained by the combination of unigrams-bigrams (accuracy = 96.04, weighted average F-measure = 95.97) closely followed by the bigrams (accuracy = 94.56%, weighted average F-measure = 94.46%) and finally unigrams (accuracy = 92.96%, weighted average F-measure = 92.90%).

Keywords: comorbidities, machine learning, obesity, Smith-Waterman algorithm

Procedia PDF Downloads 297

Authors: Chouahda Salima, Soltani Noureddine

Abstract:

The present study is a part of biological control against mosquitoes. It aims to assess the impact of two xenobiotics (a selective insect growth regulator: halofenozide and heavy metals: cadmium, more toxic and widespread in the region) in mosquitofish: Gambusia affinis. Several approaches were examined: Acute toxicity of cadmium and halofenozide: The acute toxicity of cadmium and halofenozide was examined in juvenile and adult males and females of G. affinis at different concentrations, cadmium causes mortality of the species studied with a relation dose-response. In laboratory conditions, the impact of cadmium was determined on two biomarkers of environmental stress: glutathione and acetylcholinesterase. The results show that the juvenile followed by adult males are more susceptible than adult females, while the halofenozide does not have any effect on the mortality of juvenile and adult males and females of G.affinis. Chronic toxicity of cadmium and halofenozide: both xenobiotics were added to the water fish raising at different doses tested in juveniles and adults males and females during two months of experience. Growth and metric indices; results show that halofenozide added to the water juveniles of G. affinis has no effect on their growth (length and weight). On the other side, the cadmium at the dose 5 µg/L shows a higher toxicity against juvenile, where he appears to reduce significantly their linear growth and weight. In females, the both xenobiotics have significant effects on metric indices, but these effects are more important on the hepatosomatic index that the gonadosomatic index and the coefficient of condition. Biomarkers; acetylcholinesterase (AChE), glutathione S-transferase (GST) and glutathione (GSH) used in assessing of environmental stress were measured in juveniles and adults males and females. The response of these biomarkers reveals an inhibition of AChE specific activity, an induction of GST activity, and decrease of GSH rates in juveniles in the end of experiment and during chronic treatment adult males and females. The effect of these biomarkers is more pronounced in females compared to males and juveniles. These different biomarkers have a similar profile for the duration of exposure.

Keywords: gambusia affinis, insecticide, heavy metal, morphology, biomarkers, chronic toxicity, acute toxicity, pollution

Procedia PDF Downloads 314

Authors: Mohamed Shawki Elamir, Heinrich Gotzig, Raoul Zoellner, Patrick Maeder

Abstract:

In this work, a methodology is presented for identifying the optimal digitization parameters for the analog signal of ultrasonic sensors. These digitization parameters are the resolution of the analog to digital conversion and the sampling rate. This is accomplished through the derivation of characteristic curves based on Fano inequality and the calculation of the mutual information content over a given dataset. The mutual information is calculated between the examples in the dataset and the corresponding variation in the feature that needs to be estimated. The optimal parameters are identified in a manner that ensures optimal estimation performance while preventing inefficiency in using unnecessarily powerful analog to digital converters.

Keywords: analog to digital conversion, digitization, sampling rate, ultrasonic

Procedia PDF Downloads 207

Authors: Hind Mohammed A. Asiri, Asia Mohammed Asiri, Hana Falah Alruwaili, Joseph Almazan

Abstract:

With the rapid growth of the older adult population, an underlying growth of public health concern is also seen. Various technologies were developed to help mitigate the arising problems of older adults with cognitive impairment and the improvement of their cognitive functions. This scooping review used the Joanna Briggs Institute (JBI) and the PRISMA extension for scoping reviews. The eligibility criteria were defined using the Population, Concept, Context (PCC) framework, as described in the JBI’s Reviewers Manual (Peters et al.,2020). The population of interest for this review is older adults 65 years old or older. Studies involving monitoring technology devices utilized in caring with older adult with cognitive impairment. This scoping review has shown information that researchers are more focused on creating alternative and novel methods or technological devices and use these as a tool for designing interventions depending on the data of the patient. This study has shown the type of technologies that have been explored in terms of assessing, detecting, monitoring, and interventions for cognitive impairment. Thus, there is a need for this technology to be applied in the practical field to further strengthen the evidence that it could enhance the lives of older adults.

Keywords: technology devices, cognitive impairment, older adult, nursing care, caring

Procedia PDF Downloads 123

Authors: Kriuk Boris, Kriuk Fedor

Abstract:

This paper presents a comparative study of fundamental similarity functions for Siamese networks in semantic textual similarity (STS) tasks. We evaluate various similarity functions using the STS Benchmark dataset, analyzing their performance and stability. Additionally, we introduce a multi-objective approach for optimal threshold selection. Our findings provide insights into the effectiveness of different similarity functions and offer a straightforward method for threshold selection optimization, contributing to the advancement of Siamese network architectures in STS applications.

Keywords: siamese networks, semantic textual similarity, similarity functions, STS benchmark dataset, threshold selection

Procedia PDF Downloads 37

Authors: Ahmad FAROOQ, Xinfeng Zhang, Fahad Sabah, Raheem Sarwar

Abstract:

In Traditional Chinese Medicine, tongue diagnosis is a vital inspection tool (TCM). In this study, we explore the potential of machine learning in tongue diagnosis. It begins with the cataloguing of the various classifications and characteristics of the human tongue. We infer 24 kinds of tongues from the material and coating of the tongue, and we identify 21 attributes of the tongue. The next step is to apply machine learning methods to the tongue dataset. We use the Weka machine learning platform to conduct the experiment for performance analysis. The 457 instances of the tongue dataset are used to test the performance of five different machine learning methods, including SVM, Random Forests, Decision Trees, and Naive Bayes. Based on accuracy and Area under the ROC Curve, the Support Vector Machine algorithm was shown to be the most effective for tongue diagnosis (AUC).

Keywords: medical imaging, image retrieval, machine learning, tongue

Procedia PDF Downloads 81

Authors: M. Bilal Ishfaq, Adnan N. Qureshi

Abstract:

COVID-19 is the most infectious disease these days, it was first reported in Wuhan, the capital city of Hubei in China then it spread rapidly throughout the whole world. Later on 11 March 2020, the World Health Organisation (WHO) declared it a pandemic. Since COVID-19 is highly contagious, it has affected approximately 219M people worldwide and caused 4.55M deaths. It has brought the importance of accurate diagnosis of respiratory diseases such as pneumonia and COVID-19 to the forefront. In this paper, we propose a hybrid approach for the automated detection of COVID-19 using medical imaging. We have presented the hybridization of manually extracted and convolutional features. Our approach combines Haralick texture features and convolutional features extracted from chest X-rays and CT scans. We also employ a minimum redundancy maximum relevance (MRMR) feature selection algorithm to reduce computational complexity and enhance classification performance. The proposed model is evaluated on four publicly available datasets, including Chest X-ray Pneumonia, COVID-19 Pneumonia, COVID-19 CTMaster, and VinBig data. The results demonstrate high accuracy and effectiveness, with 0.9925 on the Chest X-ray pneumonia dataset, 0.9895 on the COVID-19, Pneumonia and Normal Chest X-ray dataset, 0.9806 on the Covid CTMaster dataset, and 0.9398 on the VinBig dataset. We further evaluate the effectiveness of the proposed model using ROC curves, where the AUC for the best-performing model reaches 0.96. Our proposed model provides a promising tool for the early detection and accurate diagnosis of COVID-19, which can assist healthcare professionals in making informed treatment decisions and improving patient outcomes. The results of the proposed model are quite plausible and the system can be deployed in a clinical or research setting to assist in the diagnosis of COVID-19.

Keywords: COVID-19, feature engineering, artificial neural networks, radiology images

Procedia PDF Downloads 75

Authors: Mohamed Hendawy Mousa, Warda Youssef Mohamed Morsy

Abstract:

Background: Sepsis is a major cause of mortality and morbidity in trauma patients. Body mass index as an indicator of nutritional status was reported as a predictor of injury pattern and complications among critically ill injured patients. Aim: The aim of this study is to investigate the relationship between body mass index and the development of sepsis, systemic inflammatory response syndrome among adult trauma patients at emergency hospital - Cairo University. Research design: Descriptive correlational research design was utilized in the current study. Research questions: Q1. What is the body mass index profile of adult trauma patients admitted to the emergency hospital at Cairo University over a period of 6 months?, Q2. What is the frequency of systemic inflammatory response syndrome and sepsis among adult trauma patients admitted to the emergency hospital at Cairo University over a period of 6 months?, and Q3. What is the relationship between the development of sepsis, systemic inflammatory response syndrome and body mass index among adult trauma patients admitted to the emergency hospital at Cairo University over a period of 6 months?. Sample: A purposive sample of 52 adult male and female trauma patients with revised trauma score 10 to 12. Setting: The Emergency Hospital affiliated to Cairo University. Tools: Four tools were utilized to collect data pertinent to the study: Socio demographic and medical data tool, Systemic inflammatory response syndrome assessment tool, Revised Trauma Score tool, and Sequential organ failure assessment tool. Results: The current study revealed that, (61.5 %) of the studied subjects had normal body mass index, (25 %) were overweight, and (13.5 %) were underweight. 84.6% of the studied subjects had systemic inflammatory response syndrome and 92.3% were suffering from mild sepsis. No significant statistical relationship was found between body mass index and occurrence of Systemic inflammatory response syndrome (2= 2.89 & P = 0.23). However, Sequential organ failure assessment scores were affected significantly by body mass index was found mean of initial and last Sequential organ failure assessment score for underweight, normal and obese where t= 7.24 at p = 0.000, t= 16.49 at p = 0.000 and t= 9.80 at p = 0.000 respectively. Conclusion: Underweight trauma patients showed significantly higher rate of developing sepsis as compared to patients with normal body weight and obese. Recommendations: based on finding of this study the following are recommended: replication of the study on a larger probability sample from different geographical locations in Egypt; Carrying out of further studies in order to assess the other risk factors influencing trauma outcome and incidence of its complications; Establishment of standardized guidelines for managing underweight traumatized patients with sepsis.

Keywords: body mass index, sepsis, systemic inflammatory response syndrome, adult trauma

Procedia PDF Downloads 249

Authors: Liu Yi Hui, Chun-Liang Lai, Jhang Yu Cih, He You Jing, Chiu Fan-Yun, Lin Yu Fang

Abstract:

For universities offering long-term care education, the inclusion of adulting learning and practices in professional courses as appropriate based on holistic design and evaluation could improve talent empowerment by leveraging social capital. Moreover, it could make the courses and materials used in long-term care education responsive to real-life needs. A mixed research method was used in the research design. A quantitative study was also conducted using a questionnaire survey, and the data were analyzed by SPSS 22.0 Chinese version. The qualitative data included students’ learning files (learning reflection notes, course reports, and experience records).

Keywords: adult learning, community empowerment, social capital, mixed research

Procedia PDF Downloads 154

Authors: Hozaifa Zaki, Ghada Soliman

Abstract:

In this paper, we introduced an approach for Automated Dotted Arabic Expiration Date Extraction using Optimized Convolutional Autoencoder (ARABEX) with bidirectional LSTM. This approach is used for translating the Arabic dot-matrix expiration dates into their corresponding filled-in dates. A custom lightweight Convolutional Recurrent Neural Network (CRNN) model is then employed to extract the expiration dates. Due to the lack of available dataset images for the Arabic dot-matrix expiration date, we generated synthetic images by creating an Arabic dot-matrix True Type Font (TTF) matrix to address this limitation. Our model was trained on a realistic synthetic dataset of 3287 images, covering the period from 2019 to 2027, represented in the format of yyyy/mm/dd. We then trained our custom CRNN model using the generated synthetic images to assess the performance of our model (ARABEX) by extracting expiration dates from the translated images. Our proposed approach achieved an accuracy of 99.4% on the test dataset of 658 images, while also achieving a Structural Similarity Index (SSIM) of 0.46 for image translation on our dataset. The ARABEX approach demonstrates its ability to be applied to various downstream learning tasks, including image translation and reconstruction. Moreover, this pipeline (ARABEX+CRNN) can be seamlessly integrated into automated sorting systems to extract expiry dates and sort products accordingly during the manufacturing stage. By eliminating the need for manual entry of expiration dates, which can be time-consuming and inefficient for merchants, our approach offers significant results in terms of efficiency and accuracy for Arabic dot-matrix expiration date recognition.

Keywords: computer vision, deep learning, image processing, character recognition

Procedia PDF Downloads 82

Authors: P. Shrivastava, A. Shukla, K. Verma, S. Rungta

Abstract:

Parkinson's disease is a chronic neurological disorder that directly affects human gait. It leads to slowness of movement, causes muscle rigidity and tremors. Gait serve as a primary outcome measure for studies aiming at early recognition of disease. Using gait techniques, this paper implements efficient binary bat algorithm for an early detection of Parkinson's disease by selecting optimal features required for classification of affected patients from others. The data of 166 people, both fit and affected is collected and optimal feature selection is done using PSO and Bat algorithm. The reduced dataset is then classified using neural network. The experiments indicate that binary bat algorithm outperforms traditional PSO and genetic algorithm and gives a fairly good recognition rate even with the reduced dataset.

Keywords: parkinson, gait, feature selection, bat algorithm

Procedia PDF Downloads 545

Authors: Maassoumeh Bemani Naeini

Abstract:

Studies on interlanguage have long been engaged in describing the phenomenon of variation in SLA. Pursuing the same goal and particularly addressing the role of linguistic features, this study describes the use of Persian morphology in the interlanguage of two adult English-speaking learners of Persian L2. Taking the general approach of a combination of contrastive analysis, error analysis and interlanguage analysis, this study focuses on the identification and prediction of some possible instances of transfer from English L1 to Persian L2 across six elicitation tasks aiming to investigate whether any of contextual features may variably influence the learners’ order of morpheme accuracy in the areas of copula, possessives, articles, demonstratives, plural form, personal pronouns, and genitive cases.  Results describe the existence of task variation in the interlanguage system of Persian L2 learners.

Keywords: English L1, Interlanguage Analysis, Persian L2, SLA variation

Procedia PDF Downloads 316