Search results for: online teaching and learning

Authors: D.Mendes, J. Henriques, P. Carvalho, T. Rocha, S. Paredes, R. Cabiddu, R. Trimer, R. Mendes, A. Borghi-Silva, L. Kaminsky, E. Ashley, R. Arena, J. Myers

Abstract:

The continued exploration of clinically relevant predictive models continues to be an important pursuit. Cardiorespiratory fitness (CRF) portends clinical vital information and as such its accurate prediction is of high importance. Therefore, the aim of the current study was to develop a data-driven model, based on computational intelligence techniques and, in particular, clustering approaches, to predict CRF. Two prediction models were implemented and compared: 1) the traditional Wasserman/Hansen Equations; and 2) an interpretable clustering approach. Data used for this analysis were from the 'FRIEND - Fitness Registry and the Importance of Exercise: The National Data Base'; in the present study a subset of 10690 apparently healthy individuals were utilized. The accuracy of the models was performed through the computation of sensitivity, specificity, and geometric mean values. The results show the superiority of the clustering approach in the accurate estimation of CRF (i.e., maximal oxygen consumption).

Keywords: cardiorespiratory fitness, data-driven models, knowledge extraction, machine learning

Procedia PDF Downloads 283

Authors: Rominkumar Busa, Shahira K. C., Lijiya A.

Abstract:

Text recognition is an important area in computer vision which deals with detecting and recognising text from an image. The Optical Character Recognition (OCR) is a saturated area these days and with very good text recognition accuracy. However the same OCR methods when applied on text with small font sizes like the text data of chart images, the recognition rate is less than 30%. In this work, aims to extract small text in images using the deep learning model, CRNN with CTC loss. The text recognition accuracy is found to improve by applying image enhancement by super resolution prior to CRNN model. We also observe the text recognition rate further increases by 18% by applying the proposed method, which involves super resolution and character segmentation followed by CRNN with CTC loss. The efficiency of the proposed method shows that further pre-processing on chart image text and other small text images will improve the accuracy further, thereby helping text extraction from chart images.

Keywords: small text extraction, OCR, scene text recognition, CRNN

Procedia PDF Downloads 120

Authors: Aadhya Kaul, Gautam Manocha, Preeti Nagrath

Abstract:

Our environment comprises of a wide variety of plants that are similar to each other and sometimes the similarity between the plants makes the identification process tedious thus increasing the workload of the botanist all over the world. Now all the botanists cannot be accessible all the time for such laborious plant identification; therefore, there is an urge for a quick classification model. Also, along with the identification of the plants, it is also necessary to classify the plant as healthy or not as for a good lifestyle, humans require good food and this food comes from healthy plants. A large number of techniques have been applied to classify the plants as healthy or diseased in order to provide the solution. This paper proposes one such method known as anomaly detection using autoencoders using a set of collections of leaves. In this method, an autoencoder model is built using Keras and then the reconstruction of the original images of the leaves is done and the threshold loss is found in order to classify the plant leaves as healthy or diseased. A dataset of plant leaves is considered to judge the reconstructed performance by convolutional autoencoders and the average accuracy obtained is 71.55% for the purpose.

Keywords: convolutional autoencoder, anomaly detection, web application, FLASK

Procedia PDF Downloads 157

Authors: Alina M. Udall, Judith de Groot, Simon de Jong, Avi Shankar

Abstract:

There are many ways in which environmentally significant behavior can be explained. Dominant psychological theories, namely, the theory of planned behavior, the norm-activation theory, its extension, the value-belief-norm theory, and the theory of habit do not explain large parts of environmentally significant behaviors. A new and rapidly growing approach is to focus on how consumer’s identities predict environmentally significant behavior. Identity may be relevant because consumers have many identities that are assumed to guide their behavior. Therefore, we assume that many identities will guide environmentally significant behavior. Many identities can be relevant for environmentally significant behavior. In reviewing the literature, over 200 identities have been studied making it difficult to establish the key identities for explaining environmentally significant behavior. Therefore, this paper first aims to establish the key identities previously used for explaining environmentally significant behavior. Second, the aim is to test which key identities explain environmentally significant behavior. To address the aims, an online survey study (n = 578) is conducted. First, the exploratory factor analysis reveals 15 identity factors. The identity factors are namely, environmentally concerned identity, anti-environmental self-identity, environmental place identity, connectedness with nature identity, green space visitor identity, active ethical identity, carbon off-setter identity, thoughtful self-identity, close community identity, anti-carbon off-setter identity, environmental group member identity, national identity, identification with developed countries, cyclist identity, and thoughtful organisation identity. Furthermore, to help researchers understand and operationalize the identities, the article provides theoretical definitions for each of the identities, in line with identity theory, social identity theory, and place identity theory. Second, the hierarchical regression shows only 10 factors significantly uniquely explain the variance in environmentally significant behavior. In order of predictive power the identities are namely, environmentally concerned identity, anti-environmental self-identity, thoughtful self-identity, environmental group member identity, anti-carbon off-setter identity, carbon off-setter identity, connectedness with nature identity, national identity, and green space visitor identity. The identities explain over 60% of the variance in environmentally significant behavior, a large effect size. Based on this finding, the article reveals a new, theoretical framework showing the key identities explaining environmentally significant behavior, to help improve and align the field.

Keywords: environmentally significant behavior, factor analysis, place identity, social identity

Procedia PDF Downloads 446

Authors: Yogendra Sisodia

Abstract:

Researchers are becoming more interested in extracting useful information from legal documents thanks to the development of large-scale language models in natural language processing (NLP), and deep learning has accelerated the creation of powerful text mining models. Legal fields like contracts benefit greatly from semantic text search since it makes it quick and easy to find related clauses. After collecting sentence embeddings, it is relatively simple to locate sentences with a comparable meaning throughout the entire legal corpus. The author of this research investigated two pre-trained language models for this task: MiniLM and Roberta, and further fine-tuned them on Legal Contracts. The author used Multiple Negative Ranking Loss for the creation of sentence transformers. The fine-tuned language models and sentence transformers showed promising results.

Keywords: legal contracts, multiple negative ranking loss, natural language inference, sentence transformers, semantic textual similarity

Procedia PDF Downloads 98

Authors: Jean Paul M. Milambo

Abstract:

Purpose: Aromatase inhibitors (AIs) are indicated in the treatment of hormone-receptive breast cancer in postmenopausal women in various settings. Studies have shown cardiovascular events in some developed countries. To date the data is sparce for evidence-based recommendations in African clinical settings due to lack of cancer registries, capacity building and surveillance systems. Therefore, this study was conducted to assess the feasibility of HyBeacon® probe genotyping adjunctive to standard care for timely prediction and diagnosis of Aromatase inhibitors (AIs) associated adverse events in breast cancer survivors in Africa. Methods: Cross sectional study was conducted to assess the knowledge of POCT among six African countries using online survey and telephonically contacted. Incremental cost effectiveness ratio (ICER) was calculated, using diagnostic accuracy study. This was based on mathematical modeling. Results: One hundred twenty-six participants were considered for analysis (mean age = 61 years; SD = 7.11 years; 95%CI: 60-62 years). Comparison of genotyping from HyBeacon® probe technology to Sanger sequencing showed that sensitivity was reported at 99% (95% CI: 94.55% to 99.97%), specificity at 89.44% (95% CI: 87.25 to 91.38%), PPV at 51% (95%: 43.77 to 58.26%), and NPV at 99.88% (95% CI: 99.31 to 100.00%). Based on the mathematical model, the assumptions revealed that ICER was R7 044.55. Conclusion: POCT using HyBeacon® probe genotyping for AI-associated adverse events maybe cost effective in many African clinical settings. Integration of preventive measures for early detection and prevention guided by different subtype of breast cancer diagnosis with specific clinical, biomedical and genetic screenings may improve cancer survivorship. Feasibility of POCT was demonstrated but the implementation could be achieved by improving the integration of POCT within primary health cares, referral cancer hospitals with capacity building activities at different level of health systems. This finding is pertinent for a future envisioned implementation and global scale-up of POCT-based initiative as part of risk communication strategies with clear management pathways.

Keywords: breast cancer, diagnosis, point of care, South Africa, aromatase inhibitors

Procedia PDF Downloads 72

Authors: Getaneh Berie Tarekegn

Abstract:

Wireless communication via unmanned aerial vehicles (UAVs) has drawn a great deal of attention due to its flexibility in establishing line-of-sight (LoS) communications. However, in complex urban and dynamic environments, the movement of UAVs can be blocked by trees and high-rise buildings that obstruct directional paths. With reconfigurable intelligent surfaces (RIS), this problem can be effectively addressed. To achieve this goal, accurate channel estimation in RIS-assisted UAV-enabled wireless communications is crucial. This paper proposes an accurate channel estimation model using long short-term memory (LSTM) for a multi-user RIS-assisted UAV-enabled wireless communication system. According to simulation results, LSTM can improve the channel estimation performance of RIS-assisted UAV-enabled wireless communication.

Keywords: channel estimation, reconfigurable intelligent surfaces, long short-term memory, unmanned aerial vehicles

Procedia PDF Downloads 49

Authors: Sharmistha Chowdhury, Shuva Chowdhury

Abstract:

Buying-selling new as well as second-hand goods like tools, furniture, household, electronics, clothing, baby stuff, vehicles, and hobbies through the Facebook marketplace has become a new paradigm for c2c sellers. This phenomenon encourages and empowers decentralised home-oriented sellers. This study adopts Elaboration Likelihood Model (ELM) to explain consumer behaviour on Facebook Marketplace (FM). ELM suggests that consumers process information through the central and peripheral routes, which eventually shape their attitudes towards posts. The central route focuses on information quality, and the peripheral route focuses on cues. Sellers’ FM posts usually include product features, prices, conditions, pictures, and pick-up location. This study uses information relevance and accuracy as central route factors. The post’s attractiveness represents cues and creates positive or negative associations with the product. A post with remarkable pictures increases the attractiveness of the post. So, post aesthetics is used as a peripheral route factor. People influenced via the central or peripheral route forms an attitude that includes multiple processes – response and purchase intention. People respond to FM posts through save, share and chat. Purchase intention reflects a positive image of the product and higher purchase intention. This study proposes trust on sellers as a moderator to test the strength of its influence on consumer attitudes and behaviour. Trust on sellers is assessed whether sellers have badges or not. A sample questionnaire will be developed and distributed among a group of random FM sellers who are selling vehicles on this platform to conduct the study. The chosen product of this study is the vehicle, a high-value purchase item. High-value purchase requires consumers to consider forming their attitude without any sign of impulsiveness seriously. Hence, vehicles are the perfect choice to test the strength of consumers attitudes and behaviour. The findings of the study add to the elaboration likelihood model and online second-hand marketplace literature.

Keywords: consumer behaviour, elaboration likelihood model, facebook marketplace, c2c marketing

Procedia PDF Downloads 134

Authors: Mahbuba Rahman, Sabri Boughorbel, Scott Presnell, Charlie Quinn, Darawan Rinchai, Damien Chaussabel, Nico Marr

Abstract:

Collections of large-scale datasets made available in public repositories can be used to identify and fill gaps in biomedical knowledge. But first, these data need to be made readily accessible to researchers for analysis and interpretation. Here a collection of transcriptome datasets was made available to investigate the functional programming of human hematopoietic cells in early life. Thirty two datasets were retrieved from the NCBI Gene Expression Omnibus (GEO) and loaded in a custom, interactive web application called the Gene Expression browser (GXB), designed for visualization and query of integrated large-scale data. Multiple sample groupings and gene rank lists were created based on the study design and variables in each dataset. Web links to customized graphical views can be generated by users and subsequently be used to graphically present data in manuscripts for publication. The GXB tool also enables browsing of a single gene across datasets, which can provide information on the role of a given molecule across biological systems. The dataset collection is available online. As a proof-of-principle, one of the datasets (GSE25087) was re-analyzed to identify genes that are differentially expressed by regulatory T cells in early life. Re-analysis of this dataset and a cross-study comparison using multiple other datasets in the above mentioned collection revealed that PMCH, a gene encoding a precursor of melanin-concentrating hormone (MCH), a cyclic neuropeptide, is highly expressed in a variety of other hematopoietic cell types, including neonatal erythroid cells as well as plasmacytoid dendritic cells upon viral infection. Our findings suggest an as yet unrecognized role of MCH in immune regulation, thereby highlighting the unique potential of the curated dataset collection and systems biology approach to generate new hypotheses which can be tested in future mechanistic studies.

Keywords: early-life, GEO datasets, PMCH, interactive query, systems biology

Procedia PDF Downloads 292

Authors: Preethy Mary Donald, Renjith George

Abstract:

Oral tori are localized non-neoplastic protuberances of maxilla and mandible. Torus palatinus (TP) is found on the midline of the roof of mouth existing as single growth or in clusters. Torus mandibularis(TM) is located on the lingual aspect of the mandible commonly between canine and premolar region. Etiology of their presence was not clear and was found to be multifactorial. Their variations in relation to age, gender, ethnicity and also the characteristics of TP and TM have become the interest of multiple studies. The objectives of this study were to determine the prevalence of torus palatinus (TP) and torus mandibularis (TM) among patients who have visited outpatient department, Faculty of Dentistry, Melaka Manipal Medical College. 108 patients were examined for the presence of oral tori at the outpatient department, Faculty of Dentistry, Melaka-Manipal Medical College. Factors such as age, gender, ethnicity of the patients and size, shape, location of the oral tori were studied. For TP, Malays (62.96%) have been found to have the highest prevalence than Chinese (43.3%) and Indians (35.71%). For TM, Chinese (7.46%) had predominated compared to Malays (7.41%) and Indians (0%). There is no significant association between occurrence of TP and TM with age, gender and ethnicity. For Torus palatinus, the most common size was Grade 1(1-3mm), most common location was molar region, and the most common shape was spindle. For Torus mandibularis, the most frequent location was canine premolar region and exists in unilateral single or bilateral single fashion. The overall prevalence rates were 47.2% for TP and 6.48% for TM. However, there is no significant association between occurrence of TP and TM with age, gender and ethnicity. The results showed variations in clinical characteristics and support the findings that occurrence of tori is a dynamic phenomenon which is multifactorial owing to the environmental factors such as stress from occlusion and dietary habits. It could be due to the genetic make-up of the individual.

Keywords: torus palatinus, torus mandibularis, age, gender

Procedia PDF Downloads 272

Authors: Sheraz Akhtar

Abstract:

In recent years, a massive influx of refugees into developing countries has placed significant constraints on the host government’s capacities to provide social services, including education, to all. As a result, the refugee communities often find themselves deprived of their rights to education in these host countries, particularly for those who to live outside camps in urban locations. While previous research has examined the educational experiences of refugees who have resettled in developed nations, there remains a dearth of research on the educational experiences of urban refugees in developing nations. This study examines this issue through a case study of Pakistani Christian refugees living in urban settings in Thailand. Using a combination of observations within community learning centres set up by international non-government organisations (INGOs) working with these communities, and interviews with young Pakistani Christian refugees and their families, the research aims to give greater voice to the Pakistani Christian refugee community living in Thailand, and better understand their educational aspirations.

Keywords: Education, Developing Countries , INGOs, Urban Refugees

Procedia PDF Downloads 121

Authors: Hanan Eltayeb, Reem Al Refaie

Abstract:

To be able to connect and relate to shows spoken in a foreign language, advanced learners must understand not only linguistics inferences but also cultural, metacognitive, and pragmatic connotations in colloquial Egyptian TV series. These connotations are needed to both understand the different facets of the dramas put before them, and they’re also consistently grown and formulated through watching these shows. The inferences have become a staple in the Egyptian colloquial culture over the years, making their way into day-to-day conversations as Egyptians use them to speak, relate, joke, and connect with each other, without having known one another from previous times. As for advanced learners, they need to understand these inferences not only to watch these shows, but also to be able to converse with Egyptians on a level that surpasses the formal, or standard. When faced with some of the somewhat recent shows on the Egyptian screens, learners faced challenges in understanding pragmatics, cultural, and religious background of the target language and consequently not able to interact effectively with a native speaker in real-life situations. This study aims to enhance the linguistic and cultural proficiency of learners through studying two genres of TV Colloquial Egyptian series. Study samples derived from two recent comedian and social Egyptian series ('The Seventh Neighbor' سابع جار, and 'Nelly and Sherihan' نيللي و شريهان). When learners watch such series, they are usually faced with a problem understanding inferences that have to do with social, religious, and political events that are addressed in the series. Using discourse analysis of the sematic, semantic, pragmatic, cultural, and linguistic characteristics of the target language, some major deductions were highlighted and repeated, showing a pattern in both. The research paper concludes that there are many sets of lingual and para-lingual phrases, idioms, and proverbs to be acquired and used effectively by teaching these series. The strategies adopted in the study can be applied to different types of media, like movies, TV shows, and even cartoons, to enhance student proficiency.

Keywords: Egyptian series, culture, linguistic competence, pragmatics, semantics, social

Procedia PDF Downloads 139

Authors: Emmanuel Abayomi Rotimi

Abstract:

Context: Rabbits production plays important role in increasing animal protein supply in Nigeria. Rabbit production provides a cheap, affordable, and healthy source of meat. The growth of animals involves an increase in body weight, which can change the conformation of various parts of the body. Live weight and linear measurements are indicators of growth rate in rabbits and other farm animals. Aims: This study aimed to define the body dimensions of New Zealand rabbits and also to investigate the morphometric traits variables that contribute to body conformation by the use of principal component analysis (PCA). Methods: Data were obtained from 80 New Zealand rabbits (40 bucks and 40 does) raised in Livestock Teaching and Research Farm, Federal University Dutsinma. Data were taken on body weight (BWT), body length (BL), ear length (EL), tail length (TL), heart girth (HG) and abdominal circumference (AC). Data collected were subjected to multivariate analysis using SPSS 20.0 statistical package. Key results: The descriptive statistics showed that the mean BWT, BL, EL, TL, HG, and AC were 0.91kg, 27.34cm, 10.24cm, 8.35cm, 19.55cm and 21.30cm respectively. Sex showed significant (P<0.05) effect on all the variables examined, with higher values recorded for does. The phenotypic correlation coefficient values (r) between the morphometric traits were all positive and ranged from r = 0.406 (between EL and BL) to r = 0.909 (between AC and HG). HG is the most correlated with BWT (r = 0.786). The principal component analysis with variance maximizing orthogonal rotation was used to extract the components. Two principal components (PCs) from the factor analysis of morphometric traits explained about 80.42% of the total variance. PC1 accounted for 64.46% while PC2 accounted for 15.97% of the total variances. Three variables, representing body conformation, loaded highest in PC1. PC1 had the highest contribution (64.46%) to the total variance, and it is regarded as body conformation traits. Conclusions: This component could be used as selection criteria for improving body weight of rabbits.

Keywords: conformation, multicollinearity, multivariate, rabbits and principal component analysis

Procedia PDF Downloads 124

Authors: Barbara Rebecca Mutonyi, Chukwuemeka Echebiri, Terje Slåtten, Gudbrand Lien

Abstract:

The concept of affective commitment to change has been scarcely explored among employees in the higher education literature. The present study addresses this knowledge gap in the literature by examining how various psychological factors, such as psychological empowerment (PsyEmp), and psychological capital (PsyCap), promotes affective commitment to change. As affective commitment to change has been identified by previous studies as an important aspect to implementation behavior, the study examines the correlation of affective commitment to change on employee innovative behavior (EIB) in higher education. The study proposes mediation relationship between PsyEmp, PsyCap, and affective commitment to change. 250 employees in higher education in Norway were sampled for this study. The study employed online survey for data collection, utilizing Stata software to perform Partial least square equation modeling to test the proposed hypotheses of the study. Through bootstrapping, the study was able to test for mediating effects. Findings of the study shows a strong direct relationship between the leadership factor PsyEmp on the individual factor PsyCap ( = 0.453). In addition, the findings of the study reveal that both PsyEmp and PsyCap are related to affective commitment to change ( = 0.28 and  = 0.249, respectively). In total, PsyEmp and PsyCap explains about 10% of the variance in the concept of affective commitment to change. Further, the direct effect of effective commitment to change and EIB is also supported ( = 0.183). The three factors, PsyEmp, PsyCap, and affective commitment to change, explains nearly 40% (R2 = 0.39) of the variance found in EIB. The relationship between PsyEmp, PsyCap, and affective commitment to change are mediated through the individual factor PsyCap. In order to effectively promote affective commitment to change among higher education employees, higher education managers should focus on both the leadership factor, PsyEmp, as well as the individual factor, PsyCap, of their employees. In this regard, higher education managers should strengthen employees EIB through providing autonomy, creating a safe environment that encourages innovation thinking and action, and providing employees in higher education opportunities to be involved in changes occurring at work. This contributes to strengthening employees´ affective commitment to change, that further improves their EIB in their work roles as higher education employees. As such, the results of this study implicate the ambidextrous nature of the concepts of affective commitment to change and EIB that should be considered in future studies of innovation in higher education research.

Keywords: affective commitment to change, psychological capital, innovative behavior, psychological empowerment, higher education

Procedia PDF Downloads 114

Authors: Hossein Ghaedamini, Salman Farahbakhsh, Alireza Amirbeigi, Zahra Saghafi, Salman Daneshi, Alireza Ghaedamini

Abstract:

Background: Assessing the challenges of clinical education of medical students is one of the most important and sensitive parts of medical education. The aim of this study was to investigate the views and experiences of Kerman medical students on the factors that facilitate and inhibit the quality of clinical education. Materials and Methods: This research was qualitative and used a phenomenological approach. The study population included medical interns of Kerman University of Medical Sciences in 1400. The method of data collection was in-depth interviews with participants. Data were encoded and analyzed by Claizey stepwise model. Results: First, about 540 primary codes were extracted in the form of two main themes (facilitators and inhibitors) and 10 sub-themes including providing motivational models and creating interest in interns, high scientific level of professors and the appropriate quality of their teaching, the use of technology in the clinical education process, delegating authority and freedom of action and more responsibilities to interns, inappropriate treatment of some officials, professors, assistants and department staff with their interns, inadequate educational programming, lack of necessary cooperation and providing inappropriate treatment by clinical training experts for interns, inadequate evaluation method in clinical training for interns, poor quality mornings, the unefficiency of grand rounds, the inappropriate way of evaluating clinical training for interns, the lack of suitable facilities and conditions with the position of a medical intern, and the hardwork of some departments were categorized. Conclusion: Clinical education is always mixed with special principles and subtleties, and special attention to facilitators and inhibitors in this process has an important role in improving its quality.

Keywords: clinical education, medical students, qualitative study, education

Procedia PDF Downloads 90

Authors: Attahiru Sifawa Ahmad

Abstract:

The media; electronic, print, and social, is playing very significant roles towards promoting political awareness and stability of any nation. However, for the media to play its role effectively, a clear and sound grasp of the language of communication is necessary. Otherwise, there is the tendency of the media spreading wrong and, or, misinterpreted information to the public, capable of generating rancour and political instability. One such clear misinterpretation or misrepresentation of information was the Hausa metaphorical expression, Kare Jinni Biri Jinni quoted from the statement made by Rtd. General Muhammadu Buhari, sometimes in April, 2013, while addressing his supporters from Niger State. In the political presentation of the term Kare - Jini Biri – Jini, quoted and translated by many print media in Nigeria, it was interpreted to mean; ‘The Dog and the Baboon will be soaked in blood’, denoting bloodshed and declaration of war. However, the term Kare - jini Biri - Jini, literally; the Dog with blood and the Baboon with blood, or, the Dog is bleeding the Baboon is bleeding, or, both the Dog and the Baboon sustained injuries. It is a metaphorical expression denoting a hot competition, and serious struggle, between two competing parties that are closer in strength and stamina. The expression got its origin among the hunting communities in traditional Hausa Societies. From experience, it was always not easy to wrestle and hunt Baboon by the Hunter’s Dog. In many instances, it ended a futile exercise, and even at instances whereby the latter hunted the former, it would be after a serious struggle with both two sustaining injuries. This paper seeks to highlight the poverty of vocabulary, and poor grasp of Nigerian languages among Journalists and young citizens in the country. The paper, therefore, advocated for the retention and effective teaching of the indigenous languages in primary and secondary school’s curriculums in Nigeria. The paper equally analysed the political origin of the print media in Nigeria, how since its first appearance, the print Media is being assigned very important political role by political elites in the country.

Keywords: Baboon, dog, media, politics

Procedia PDF Downloads 216

Authors: H. Zidoum, A. AlShareedah, S. Al Sawafi, A. Al-Ansari, B. Al Lawati

Abstract:

Systemic lupus erythematosus (SLE) is an autoimmune disease with genetic and environmental components. SLE is characterized by a wide variability of clinical manifestations and a course frequently subject to unpredictable flares. Despite recent progress in classification tools, the early diagnosis of SLE is still an unmet need for many patients. This study proposes an interpretable disease classification model that combines the high and efficient predictive performance of CatBoost and the model-agnostic interpretation tools of Shapley Additive exPlanations (SHAP). The CatBoost model was trained on a local cohort of 219 Omani patients with SLE as well as other control diseases. Furthermore, the SHAP library was used to generate individual explanations of the model's decisions as well as rank clinical features by contribution. Overall, we achieved an AUC score of 0.945, F1-score of 0.92 and identified four clinical features (alopecia, renal disorders, cutaneous lupus, and hemolytic anemia) along with the patient's age that was shown to have the greatest contribution on the prediction.

Keywords: feature selection, classification, systemic lupus erythematosus, model interpretation, SHAP, Catboost

Procedia PDF Downloads 77

Authors: DEVASHISH KHULBE, MANU PATHAK

Abstract:

The rise in popularity of major social media platforms have enabled people to share photos and textual information about their daily life. One of the popular topics about which information is shared is food. Since a lot of media about food are attributed to particular locations and restaurants, information like spatio-temporal popularity of various cuisines can be analyzed. Tracking the popularity of food types and retail locations across space and time can also be useful for business owners and restaurant investors. In this work, we present an approach using off-the shelf machine learning techniques to identify trends and popularity of cuisine types in an area using geo-tagged data from social media, Google images and Yelp. After adjusting for time, we use the Kernel Density Estimation to get hot spots across the location and model the dependencies among food cuisines popularity using Bayesian Networks. We consider the Manhattan borough of New York City as the location for our analyses but the approach can be used for any area with social media data and information about retail businesses.

Keywords: Web Mining, Geographic Information Systems, Business popularity, Spatial Data Analyses

Procedia PDF Downloads 111

Authors: Vasupradaa Manivannan, Santosh Maruthy

Abstract:

Background/Aims: Preliminary evidence suggests that code-switching and code-mixing may act as one of the voluntary coping behavior to avoid the stuttering characteristics in children and adults; however, less is known about the types and patterns of code-mixing (CM) and code-switching (CS). Further, it is not known how it is different between children to adults who stutter. This study aimed to identify and compare the CM and CS patterns between Kannada-English bilingual children and adults who stutter. Method: A standard group comparison was made between five children who stutter (CWS) in the age range of 9-13 years and five adults who stutter (AWS) in the age range of 20-25 years. The participants who are proficient in Kannada (first language- L1) and English (second language- L2) were considered for the study. There were two tasks given to both the groups, a) General conversation (GC) with 10 random questions, b) Narration task (NAR) (Story / General Topic, for example., A Memorable Life Event) in three different conditions {Mono Kannada (MK), Mono English (ME), and Bilingual (BIL) Condition}. The children and adults were assessed online (via Zoom session) with a high-quality internet connection. The audio and video samples of the full assessment session were auto-recorded and manually transcribed. The recorded samples were analyzed for the percentage of dysfluencies using SSI-4 and CM, and CS exhibited in each participant using Matrix Language Frame (MLF) model parameters. The obtained data were analyzed using the Statistical Package for the Social Sciences (SPSS) software package (Version 20.0). Results: The mean, median, and standard deviation values were obtained for the percentage of dysfluencies (%SS) and frequency of CM and CS in Kannada-English bilingual children and adults who stutter for various parameters obtained through the MLF model. The inferential results indicated that %SS significantly varied between population (AWS vs CWS), languages (L1 vs L2), and tasks (GC vs NAR) but not across free (BIL) and bound (MK, ME) conditions. It was also found that the frequency of CM and CS patterns varies between CWS and AWS. The AWS had a lesser %SS but greater use of CS patterns than CWS, which is due to their excessive coping skills. The language mixing patterns were more observed in L1 than L2, and it was significant in most of the MLF parameters. However, there was a significantly higher (P<0.05) %SS in L2 than L1. The CS and CS patterns were more in conditions 1 and 3 than 2, which may be due to the higher proficiency of L2 than L1. Conclusion: The findings highlight the importance of assessing the CM and CS behaviors, their patterns, and the frequency of CM and CS between CWS and AWS on MLF parameters in two different tasks across three conditions. The results help us to understand CM and CS strategies in bilingual persons who stutter.

Keywords: bilinguals, code mixing, code switching, stuttering

Procedia PDF Downloads 72

Authors: R. Biondi, G. Dys, G. Ferone, T. Renard, M. Zysman

Abstract:

This paper describes an automated implementable system for impulsive signals detection and recognition. The system uses a Digital Signal Processing device for the detection and identification process. Here the system analyses the signals in real time in order to produce a particular response if needed. The system analyses the signals in real time in order to produce a specific output if needed. Detection is achieved through normalizing the inputs and comparing the read signals to a dynamic threshold and thus avoiding detections linked to loud or fluctuating environing noise. Identification is done through neuronal network algorithms. As a setup our system can receive signals to “learn” certain patterns. Through “learning” the system can recognize signals faster, inducing flexibility to new patterns similar to those known. Sound is captured through a simple jack input, and could be changed for an enhanced recording surface such as a wide-area recorder. Furthermore a communication module can be added to the apparatus to send alerts to another interface if needed.

Keywords: sound detection, impulsive signal, background noise, neural network

Procedia PDF Downloads 314

Authors: Saima Nazir, Mustansar Ali Ghazanfar, Sanay Muhammad Umar Saeed, Muhammad Awais Azam, Saad Ali Alahmari

Abstract:

Terrorism is an important and challenging concern. The entire world is threatened by only few sophisticated terrorist groups and especially in Gulf Region and Pakistan, it has become extremely destructive phenomena in recent years. Predicting the pattern of attack type, attack group and target type is an intricate task. This study offers new insight on terrorist group’s attack type and its chosen target. This research paper proposes a framework for prediction of terrorist attacks using the historical data and making an association between terrorist group, their attack type and target. Analysis shows that the number of attacks per year will keep on increasing, and Al-Harmayan in Saudi Arabia, Al-Qai’da in Gulf Region and Tehreek-e-Taliban in Pakistan will remain responsible for many future terrorist attacks. Top main targets of each group will be private citizen & property, police, government and military sector under constant circumstances.

Keywords: data mining, counter terrorism, machine learning, SVM

Procedia PDF Downloads 403

Authors: Neşe Alkan

Abstract:

Purpose: The point that applied/clinical psychology, which is the practice and research discipline of the mental health field, has reached today can be summarized as the necessity of handling the psychological well-being of people from multiple perspectives and the goal of moving it to a higher level. Clients' subjective assessment of their own condition and wellbeing is an integral part of evidence-based interventions. There is a need for tools through which clients can evaluate the effectiveness of the psychotherapy/intervention performed with them and their contribution to the wellbeing and wellbeing of this process in a valid and reliable manner. The aim of this research is to meet this need, to test the reliability and validity of the index in Turkish, and explore its usability in the practices of both researchers and psychotherapists. Method: A total of 213 adults aged between 18-54, 69.5% working and 29.5% university students, were included in the study. Along with their demographic information, the participants were administered a set of scales: wellbeing, life satisfaction, spiritual satisfaction, shopping addiction, and loneliness, namely via an online platform. The construct validity of the wellbeing scale was tested with exploratory and confirmatory factor analyses, convergent and discriminant validity were tested with two-way full and partial correlation analyses and, measurement invariance was tested with one-way analysis of variance. Results: Factor analyzes showed that the scale consisted of six dimensions as it is in its original structure. The internal consistency of the scale was found to be Cronbach α = .82. Two-way correlation analyzes revealed that the wellbeing scale total score was positively correlated with general life satisfaction (r = .62) and spiritual satisfaction (r = .29), as expected. It was negatively correlated with loneliness (r = -.51) and shopping addiction (r = -.15). While the scale score did not vary by gender, previous illness, or nicotine addiction, it was found that the total wellbeing scale scores of the participants who had used antidepressant medication during the past year were lower than those who did not use antidepressant medication (F(1,204) = 7.713, p = .005). Conclusion: It has been concluded that the 12-item wellbeing scale consisting of six dimensions can be used in research and health sciences practices as a valid and reliable measurement tool. Further research which examines the reliability and validity of the scale in different widely used languages such as Spanish and Chinese is recommended.

Keywords: wellbeing, intervention effectiveness, reliability and validity, effectiveness

Procedia PDF Downloads 176

Authors: Iman Dwi Almunandar, Nellawaty A. Tewu, Anshari Al Ghaniyy

Abstract:

The emergence of academic procrastination behavior among students in Indonesian, especially the students of Faculty of Psychology at YARSI University becomes a habit to be underestimated, so often interfere with the effectiveness of learning process. The lecturers at the Faculty of Psychology YARSI University have very often warned students to be able to do and collect assignments accordance to predetermined deadline. However, they are still violated it. According to researchers, this problem needs to do a proper training for the solution to minimize academic procrastination behavior on students. In this study, researchers conducted analyze needs for deciding whether need the training or not. Number of sample is 30 respondents which being choose with a simple random sampling. Measurement of academic procrastination behavior is using the theory by McCloskey (2011), there are six dimensions: Psychological Belief about Abilities, Distractions, Social Factor of Procrastination, Time Management, Personal Initiative, Laziness. Methods of analyze needs are using Questioner, Interview, Observations, Focus Group Discussion (FGD), Intelligence Tests. The result of analyze needs shows that psychology students generation of 2015 at the Faculty of Psychology YARSI University need for training on Time Management.

Keywords: procrastination, psychology, analyze needs, behavior

Procedia PDF Downloads 372

Authors: Yu Zhang, Pedro Desouza

Abstract:

Since big data has become substantially more accessible and manageable due to the development of powerful tools for dealing with unstructured data, people are eager to mine information from social media resources that could not be handled in the past. Sentiment analysis, as a novel branch of text mining, has in the last decade become increasingly important in marketing analysis, customer risk prediction and other fields. Scientists and researchers have undertaken significant work in creating and improving their sentiment models. In this paper, we present a concept of selecting appropriate classifiers based on the features and qualities of data sources by comparing the performances of five classifiers with three popular social media data sources: Twitter, Amazon Customer Reviews, and Movie Reviews. We introduced a couple of innovative models that outperform traditional sentiment classifiers for these data sources, and provide insights on how to further improve the predictive power of sentiment analysis. The modelling and testing work was done in R and Greenplum in-database analytic tools.

Keywords: sentiment analysis, social media, Twitter, Amazon, data mining, machine learning, text mining

Procedia PDF Downloads 346

Authors: Laura Brennan, Ram Balakumar

Abstract:

ChatGPT has been developed by Open AI (Nov 2022) as a powerful artificial intelligence (AI) language model which has been designed to produce human-like text from user written prompts. To gain the most from the system, user written prompts must give context specific information. This article aims to give guidance on how to optimise the ChatGPT system in the context of education for otolaryngology. Otolaryngology is a specialist field which sees little time dedicated to providing education to both medical students and doctors. Additionally, otolaryngology trainees have seen a reduction in learning opportunities since the COVID-19 pandemic. In this article we look at these various barriers to medical education in Otolaryngology training and suggest ways that ChatGPT can overcome them and assist in simulation-based training. Examples provide how this can be achieved using the Authors’ experience to further highlight the practicalities. What this article has found is that while ChatGPT cannot replace traditional mentorship and practical surgical experience, it can serve as an invaluable supplementary resource to simulation based medical education in Otolaryngology.

Keywords: artificial intelligence, otolaryngology, surgical training, medical education

Procedia PDF Downloads 148

Authors: Abu S. Mustafa, Mohammad W. Khan, Faraz Shaheed Khan, Nazima Habibi

Abstract:

Brucellosis is a zoonotic disease of worldwide prevalence. There are at least four species and several strains of Brucella that cause human disease. Brucella genomes have very limited variation across strains, which hinder strain identification using classical molecular techniques, including PCR and 16 S rDNA sequencing. The aim of this study was to perform whole genome sequencing of clinical isolates of Brucella and perform bioinformatics and comparative genomics analyses to determine the existence of genetic differences across the isolates of a single Brucella species and strain. The draft sequence data were generated from 15 clinical isolates of Brucella melitensis (biovar 2 strain 63/9) using MiSeq next generation sequencing platform. The generated reads were used for further assembly and analysis. All the analysis was performed using Bioinformatics work station (8 core i7 processor, 8GB RAM with Bio-Linux operating system). FastQC was used to determine the quality of reads and low quality reads were trimmed or eliminated using Fastx_trimmer. Assembly was done by using Velvet and ABySS softwares. The ordering of assembled contigs was performed by Mauve. An online server RAST was employed to annotate the contigs assembly. Annotated genomes were compared using Mauve and ACT tools. The QC score for DNA sequence data, generated by MiSeq, was higher than 30 for 80% of reads with more than 100x coverage, which suggested that data could be utilized for further analysis. However when analyzed by FastQC, quality of four reads was not good enough for creating a complete genome draft so remaining 11 samples were used for further analysis. The comparative genome analyses showed that despite sharing same gene sets, single nucleotide polymorphisms and insertions/deletions existed across different genomes, which provided a variable extent of diversity to these bacteria. In conclusion, the next generation sequencing, bioinformatics, and comparative genome analysis can be utilized to find variations (point mutations, insertions and deletions) across different genomes of Brucella within a single strain. This information could be useful in surveillance and epidemiological studies supported by Kuwait University Research Sector grants MI04/15 and SRUL02/13.

Keywords: brucella, bioinformatics, comparative genomics, whole genome sequencing

Procedia PDF Downloads 375

Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei

Abstract:

With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.

Keywords: document processing, framework, formal definition, machine learning

Procedia PDF Downloads 208

Authors: Sezin Ekşioğlu

Abstract:

Multilabel classification has a huge importance for several applications, it is also a challenging research topic. It is a kind of supervised learning that contains binary targets. The distance between multilabel and binary classification is having more than one class in multilabel classification problems. Features can belong to one class or many classes. There exists a wide range of applications for multi label prediction such as image labeling, text categorization, gene functionality. Even though features are classified in many classes, they may not always be properly classified. There are many ensemble methods for the classification. However, most of the researchers have been concerned about better multilabel methods. Especially little ones focus on both efficiency of classifiers and pairwise relationships at the same time in order to implement better multilabel classification. In this paper, we worked on modified ensemble methods by getting benefit from k-Nearest Neighbors and neural network structure to address issues within a beneficial way and to get better impacts from the multilabel classification. Publicly available datasets (yeast, emotion, scene and birds) are performed to demonstrate the developed algorithm efficiency and the technique is measured by accuracy, F1 score and hamming loss metrics. Our algorithm boosts benchmarks for each datasets with different metrics.

Keywords: multilabel, classification, neural network, KNN

Procedia PDF Downloads 149

Authors: Bartelsen-Raemy Annabelle, Gerber Andrea

Abstract:

Objectives: The adoption of the UN Convention on the Rights of Persons with Disabilities has the effect that higher education institutions in Switzerland are called upon to promote inclusive university education. In this context, our School of Social Work aims to provide fair participation and the removal of barriers in our study programmes at bachelor’s and master’s levels. In 2015 we developed a concept of reasonable adjustments for students with disabilities and chronic illness as an instrument to provide equal opportunities for those students. We reviewed the implementation of this concept as part of our quality management process. Using a qualitative research design, we explored how affected students and lecturers experience the processes and measures taken and which barriers they still perceive. Methods: We captured subjective perspectives and experience of measures by conducting 15 problem-centred interviews with affected students and three experimental focus groups with lecturers. The data was processed using structured qualitative content analysis and summarised as key categories. Results: All respondents evaluated the concept of reasonable adjustment very positively and emphasised its importance for equal opportunities. Our analysis revealed differences in the usage and perception of both groups and showed that the students interviewed were a heterogeneous group with different needs. Overall, the students described the adjustments, in particular in relation to examinations and other assignments, as a great relief. The lecturers expressed high standards for their own teaching and supervision of students and, at the same time, wished for more support from the university. However, despite the positive evaluation by the lecturers, the limits of reasonable adjustment became evident. It is necessary to consider the limits of reasonable adjustments in terms of professional skills. Conclusion: Reasonable adjustments should, therefore, be seen as an element of an inclusive university culture that must be complemented by further measures. Taking this into account, we have planned further research as a basis for the development of a diversity and inclusion policy.

Keywords: opportunities and limits, reasonable adjustment, social work education, students with disabilities

Procedia PDF Downloads 129

Authors: John Acord, Ankita Batla, Kiran Khepar, Maude Schmidt, Charlotte Allen, Russ Bradford

Abstract:

Objectives: Despite the availability oftreatment options, Parkinson’s disease (PD) continues to impact heavily on a patient’s quality of life (QoL), as many symptoms that bother the patient remain unexplored and untreated in clinical settings. The aims of this research were to understand the burden of PDsymptoms from a patient perspective, particularly those which are the most persistent and debilitating, and to determine if current treatments and treatment algorithms adequately focus on their resolution. Methods: A13-question, online, patient-reported survey was created based on the MDS-Unified Parkinson’s Disease Rating Scale (MDS-UPDRS)and symptoms listed on Parkinson’s Disease Patient Advocacy Groups websites, and then validated by 10 Parkinson’s patients. In the survey, patients were asked to choose both their most common and their most bothersome symptoms, whether they had received treatment for those and, if so, had it been effective in resolving those symptoms. Results: The most bothersome symptoms reported by the 111 participants who completed the survey were sleep problems (61%), feeling tired (56%), slowness of movements (54%), and pain in some parts of the body (49%). However, while 86% of patients reported receiving dopamine or dopamine like drugs to treat their PD, far fewer reported receiving targeted therapies for additional symptoms. For example, of the patients who reported having sleep problems, only 33% received some form of treatment for this symptom. This was also true for feeling tired (30% received treatment for this symptom), slowness of movements (62% received treatment for this symptom), and pain in some parts of the body (61% received treatment for this symptom). Additionally, 65% of patients reported that the symptoms they experienced were not adequately controlled by the treatments they received, and 9% reported that their current treatments had no effect on their symptoms whatsoever. Conclusion: The survey outcomes highlight that the majority of patients involved in the study received treatment focused on their disease, however, symptom-based treatments were less well represented. Consequently, patient-reported symptoms such as sleep problems and feeling tired tended to receive more fragmented intervention than ‘classical’ PD symptoms, such as slowness of movement, even though they were reported as being amongst the most bothersome symptoms for patients. This research highlights the need to explore symptom burden from the patient’s perspective and offer Customised treatment/support for both motor and non-motor symptoms maximize patients’ quality of life.

Keywords: survey, patient reported symptom burden, unmet needs, parkinson's disease

Procedia PDF Downloads 288