Search results for: in-context learning (ICL)

Authors: Rosa Tsegaye Aga, Xuan Jiang, Pavel Vazquez Faci, Siqing Liu, Simon Rayner, Endalkachew Alemu, Markos Abebe

Abstract:

Tuberculosis (TB) is a major cause of disease globally. In most cases, TB is treatable and curable, but only with the proper treatment. There is a time when drug-resistant TB occurs when bacteria become resistant to the drugs that are used to treat TB. Current strategies to identify drug-resistant TB bacteria are laboratory-based, and it takes a longer time to identify the drug-resistant bacteria and treat the patient accordingly. But machine learning (ML) and data science approaches can offer new approaches to the problem. In this study, we propose to develop an ML-based model to predict the antibiotic resistance phenotypes of TB isolates in minutes and give the right treatment to the patient immediately. The study has been using the whole genome sequence (WGS) of TB isolates as training data that have been extracted from the NCBI repository and contain different countries’ samples to build the ML models. The reason that different countries’ samples have been included is to generalize the large group of TB isolates from different regions in the world. This supports the model to train different behaviors of the TB bacteria and makes the model robust. The model training has been considering three pieces of information that have been extracted from the WGS data to train the model. These are all variants that have been found within the candidate genes (F1), predetermined resistance-associated variants (F2), and only resistance-associated gene information for the particular drug. Two major datasets have been constructed using these three information. F1 and F2 information have been considered as two independent datasets, and the third information is used as a class to label the two datasets. Five machine learning algorithms have been considered to train the model. These are Support Vector Machine (SVM), Random forest (RF), Logistic regression (LR), Gradient Boosting, and Ada boost algorithms. The models have been trained on the datasets F1, F2, and F1F2 that is the F1 and the F2 dataset merged. Additionally, an ensemble approach has been used to train the model. The ensemble approach has been considered to run F1 and F2 datasets on gradient boosting algorithm and use the output as one dataset that is called F1F2 ensemble dataset and train a model using this dataset on the five algorithms. As the experiment shows, the ensemble approach model that has been trained on the Gradient Boosting algorithm outperformed the rest of the models. In conclusion, this study suggests the ensemble approach, that is, the RF + Gradient boosting model, to predict the antibiotic resistance phenotypes of TB isolates by outperforming the rest of the models.

Keywords: machine learning, MTB, WGS, drug resistant TB

Procedia PDF Downloads 52

Authors: Mercedes Rodriguez Sanchez, Laura Luceño Casals

Abstract:

With the rise of social media, creative people and brands everywhere are constantly generating content. The students with Bachelor's Degrees in Fashion Design use platforms such as Instagram or TikTok to look for inspiration and entertainment, as well as a way to develop their own ideas and share them with a wide audience. Information and Communications Technologies (ICT) have become a central aspect of higher education, virtually affecting every aspect of the student experience. Following the current trend, during the first semester of the second year, a collaborative project across two subjects –Design Management and History of Fashion Design– was implemented. After an introductory class focused on the relationship between fashion and cinema, as well as a brief history of 20th-century fashion, the students freely chose a work team and an iconic look from a movie costume. They researched the selected movie and its sociocultural context, analyzed the costume and the work of the designer, and studied the style, fashion magazines and most popular films of the time. Students then redesigned and recreated the costume, for which they were compelled to recycle the materials they had available at home as an unavoidable requirement of the activity. Once completed the garment, students delivered in-class, team-based presentations supported by the final design, a project summary poster and a making-of video, which served as a documentation tool of the costume design process. The methodologies used include Challenge-Based Learning (CBL), debates, Internet research, application of Information and Communications Technologies, and viewing clips of classic films, among others. After finishing the projects, students were asked to complete two electronic surveys to measure the acquisition of transversal and specific competencies of each subject. Results reveal that this activity helped the students' knowledge acquisition, a deeper understanding of both subjects and their skills development. The classroom dynamic changed. The multidisciplinary approach encouraged students to collaborate with their peers, while educators were better able to keep students' interest and promote an engaging learning process. As a result, the activity discussed in this paper confirmed the research hypothesis: it is positive to propose innovative teaching projects that combine academic research with playful learning environments.

Keywords: cinema, cooperative learning, fashion design, higher education, upcycling

Procedia PDF Downloads 78

Authors: Maja S. Todorovic

Abstract:

This paper aims to promote entrepreneurial storytelling by exploring new ideas and learning practices. An entrepreneur needs to be a ‘storyteller’, an ‘epic hero’, capable of offering an emotional connection to his audience, a character with whom audience can identify with, rejoice, suffer, celebrate, fail – simply experience everything. In other words, a successful entrepreneur is giving tangible experience through his business story and that’s what makes his story and business alive. Use of mythology, eulogy, metaphor, epic, fairytales and cartoons, permeated with humor and sudden twists is a winning recipe for a business story that captures attention. In the business case of the Greenesignit! Card game, (educational and brainstorming tool for development of sustainable products) we will demonstrate how an entrepreneur successfully used visual narrative to communicate his story and at the same time as a vehicle to transmute his message in learning tool and product development.

Keywords: animating narrative, entrepreneur, Greeneisgnit! card game, visual storytelling

Procedia PDF Downloads 392

Authors: Minh Huynh, Aaron Heuser, Luke Patterson, Chris Zhang, Mason Miller, Daniel Wang, Sandeep Shetty, Mike Trinh, Abigail Miller, Adaeze Enekwechi, Tenille Daniels, Lu Huynh

Abstract:

Machine learning and text analytics have been used to analyze child abuse, cyberbullying, domestic abuse and domestic violence, and hate speech. However, to the authors’ knowledge, no research to date has used these methods to study elder abuse in nursing homes or skilled nursing facilities from field inspection reports. We used machine learning and text analytics methods to analyze 356,000 inspection reports, which have been extracted from CMS Form-2567 field inspections of US nursing homes and skilled nursing facilities between 2016 and 2021. Our algorithm detected occurrences of the various types of abuse, including physical abuse, psychological abuse, verbal abuse, sexual abuse, and passive and active neglect. For example, to detect physical abuse, our algorithms search for combinations or phrases and words suggesting willful infliction of damage (hitting, pinching or burning, tethering, tying), or consciously ignoring an emergency. To detect occurrences of elder neglect, our algorithm looks for combinations or phrases and words suggesting both passive neglect (neglecting vital needs, allowing malnutrition and dehydration, allowing decubiti, deprivation of information, limitation of freedom, negligence toward safety precautions) and active neglect (intimidation and name-calling, tying the victim up to prevent falls without consent, consciously ignoring an emergency, not calling a physician in spite of indication, stopping important treatments, failure to provide essential care, deprivation of nourishment, leaving a person alone for an inappropriate amount of time, excessive demands in a situation of care). We further compare the prevalence of abuse before and after Covid-19 related restrictions on nursing home visits. We also identified the facilities with the most number of cases of abuse with no abuse facilities within a 25-mile radius as most likely candidates for additional inspections. We also built an interactive display to visualize the location of these facilities.

Keywords: machine learning, text analytics, elder abuse, elder neglect, nursing home abuse

Procedia PDF Downloads 146

Authors: Linda Blümel, Bettina Bert, Jan Brosda, Heidrun Fink, Melanie Hamann

Abstract:

Age-related cognitive decline can eventually lead to dementia, the most common mental illness in elderly people and an immense challenge for patients, their families and caregivers. Cholinesterase inhibitors constitute the most commonly used antidementia prescription medication. The standardized Ginkgo biloba leaf extract EGb 761® is approved for treating age-associated cognitive impairment and has been shown to improve the quality of life in patients suffering from mild dementia. A clinical trial with 96 Alzheimer´s disease patients indicated that the combined treatment with donepezil and EGb 761® had fewer side effects than donepezil alone. In an animal model of cognitive aging, we compared the effect of combined treatment with EGb 761® or donepezil monotherapy and vehicle. We compared the effect of chronic treatment (15 days of pretreatment) with donepezil (1.5 mg/kg p. o.), EGb 761® (100 mg/kg p. o.), or the combination of the two drugs, or vehicle in 18 – 20 month old male OFA rats. Learning and memory performance were assessed by Morris water maze testing, motor behavior in an open field paradigm. In addition to chronic treatment, the substances were administered orally 30 minutes before testing. Compared to the first day and to the control group, only the combination group showed a significant reduction in latency to reach the hidden platform on the second day of testing. Moreover, from the second day of testing onwards, the donepezil, the EGb 761® and the combination group required less time to reach the hidden platform compared to the first day. The control group did not reach the same latency reduction until day three. There were no effects on motor behavior. These results suggest a superiority of the combined treatment of donepezil with EGb 761® compared to monotherapy.

Keywords: age-related cognitive decline, dementia, ginkgo biloba leaf extract EGb 761®, learning and memory, old rats

Procedia PDF Downloads 368

Authors: Regis Pochon, Nicolas Stefaniak, Veronique Baltazart, Pamela Gobin

Abstract:

Anxiety is known to have an impact on working memory. In reasoning or memory tasks, individuals with anxiety tend to show longer response times and poorer performance. Furthermore, there is a memory bias for negative information in anxiety. Given the crucial role of working memory in lexical learning, anxious students may encounter more difficulties in learning to read and spell. Anxiety could even affect an earlier learning, that is the activation of phonological representations, which are decisive for the learning of reading and writing. The aim of this study is to compare the access to phonological representations of beginning readers and writers according to their level of anxiety, using an auditory lexical decision task. Eighty students of 6- to 9-years-old completed the French version of the Revised Children's Manifest Anxiety Scale and were then divided into four anxiety groups according to their total score (Low, Median-Low, Median-High and High). Two set of eighty-one stimuli (words and non-words) have been auditory presented to these students by means of a laptop computer. Stimuli words were selected according to their emotional valence (positive, negative, neutral). Students had to decide as quickly and accurately as possible whether the presented stimulus was a real word or not (lexical decision). Response times and accuracy were recorded automatically on each trial. It was anticipated a) longer response times for the Median-High and High anxiety groups in comparison with the two others groups, b) faster response times for negative-valence words in comparison with positive and neutral-valence words only for the Median-High and High anxiety groups, c) lower response accuracy for Median-High and High anxiety groups in comparison with the two others groups, d) better response accuracy for negative-valence words in comparison with positive and neutral-valence words only for the Median-High and High anxiety groups. Concerning the response times, our results showed no difference between the four groups. Furthermore, inside each group, the average response times was very close regardless the emotional valence. Otherwise, group differences appear when considering the error rates. Median-High and High anxiety groups made significantly more errors in lexical decision than Median-Low and Low groups. Better response accuracy, however, is not found for negative-valence words in comparison with positive and neutral-valence words in the Median-High and High anxiety groups. Thus, these results showed a lower response accuracy for above-median anxiety groups than below-median groups but without specificity for the negative-valence words. This study suggests that anxiety can negatively impact the lexical processing in young students. Although the lexical processing speed seems preserved, the accuracy of this processing may be altered in students with moderate or high level of anxiety. This finding has important implication for the prevention of reading and spelling difficulties. Indeed, during these learnings, if anxiety affects the access to phonological representations, anxious students could be disturbed when they have to match phonological representations with new orthographic representations, because of less efficient lexical representations. This study should be continued in order to precise the impact of anxiety on basic school learning.

Keywords: anxiety, emotional valence, childhood, lexical access

Procedia PDF Downloads 288

Authors: Morolake Josephine Adeagbo

Abstract:

South Africa is one of those countries that openly rejected racism, and this is entrenched in its Bill of Rights. Despite the acceptance and incorporation of racial integration into the South Africa Constitution, the implementation within some sectors, most especially the educational sector, seems difficult. Recent occurrences of racism in some higher institutions of learning in South Africa are indications that racial integration / racial transformation is still farfetched in the country’s higher educational sector. It is against this background that this study was conducted to understand how gender and residential background influence racial integration in a South African university which was predominantly a white Afrikaner institution. Using a quantitative method to test the attitude of different categories of undergraduate students at the university, this study found that the factors- residential background and gender- used in measuring student’s attitude do not necessarily have a significant relationship towards racial integration. However, this study concludes with a call for more research with a range of other factors in order to better understand how racial integration can be promoted in South African institutions of higher learning.

Keywords: racial integration, gender, residential background, transformation

Procedia PDF Downloads 442

Authors: Mohini Mohamed, Nurul Huda Mas’od

Abstract:

This study was aimed at designing and developing an assistive mathematical teaching aid (courseware) in helping dyslexic students in learning multiplication. Computers and multimedia interactive courseware has benefits students in terms of increase learner’s motivation and engage them to stay on task in classroom. Most disability student has short attention span thus with the advantage offered by multimedia interactive courseware allows them to retain the learning process for longer period as compared to traditional chalk and talk method. This study was conducted in a public school at a primary level with the help of three special education teachers and six dyslexic students as participants. Qualitative methodology using interview with special education teachers and observations in classes were conducted. The development of the multimedia interactive courseware in this study was divided to three processes which were analysis and design, development and evaluation. The courseware was evaluated by using User Acceptance Survey Form and interview. Feedbacks from teachers were used to alter, correct and develop the application for a better multimedia interactive courseware.

Keywords: disability students, dyslexia, mathematics teaching aid, multimedia interactive courseware

Procedia PDF Downloads 403

Authors: Pradeep Singh, Shrish Verma

Abstract:

Software fault prediction models are created by using the source code, processed metrics from the same or previous version of code and related fault data. Some company do not store and keep track of all artifacts which are required for software fault prediction. To construct fault prediction model for such company, the training data from the other projects can be one potential solution. The earlier we predict the fault the less cost it requires to correct. The training data consists of metrics data and related fault data at function/module level. This paper investigates fault predictions at early stage using the cross-project data focusing on the design metrics. In this study, empirical analysis is carried out to validate design metrics for cross project fault prediction. The machine learning techniques used for evaluation is Naïve Bayes. The design phase metrics of other projects can be used as initial guideline for the projects where no previous fault data is available. We analyze seven data sets from NASA Metrics Data Program which offer design as well as code metrics. Overall, the results of cross project is comparable to the within company data learning.

Keywords: software metrics, fault prediction, cross project, within project.

Procedia PDF Downloads 344

Authors: Elnaz Lashgari, Emel Demircan

Abstract:

Electromyography (EMG) is one of the most important interfaces between humans and robots for rehabilitation. Decoding this signal helps to recognize muscle activation and converts it into smooth motion for the robots. Detecting each muscle’s pattern during walking and running is vital for improving the quality of a patient’s life. In this study, EMG data from 10 muscles in 10 subjects at 4 different speeds were analyzed. EMG signals are nonlinear with high dimensionality. To deal with this challenge, we extracted some features in time-frequency domain and used manifold learning and Laplacian Eigenmaps algorithm to find the intrinsic features that represent data in low-dimensional space. We then used the Bayesian classifier to identify various patterns of EMG signals for different muscles across a range of running speeds. The best result for vastus medialis muscle corresponds to 97.87±0.69 for sensitivity and 88.37±0.79 for specificity with 97.07±0.29 accuracy using Bayesian classifier. The results of this study provide important insight into human movement and its application for robotics research.

Keywords: electromyography, manifold learning, ISOMAP, Laplacian Eigenmaps, locally linear embedding

Procedia PDF Downloads 362

Authors: Kunto Nurcahyoko

Abstract:

The fundamental perception used in this study is that teaching and learning activities in Indonesian classroom have potentially generated individual’s sensitivity on cross-cultural understanding. This study aims at investigating Indonesian university students’ perception on cross-cultural understanding after doing Cultural Snapshot Project. The data was critically analyzed through multicultural ideology and diversity theories. The subjects were 30 EFL college students in one of colleges in Indonesia. Each student was assigned to capture a photo which depicted the existence of any cultural manifestation in their surrounding such as discrimination, prejudice and stereotype. Students were then requested asked to reflect on the picture by writing a short description on the picture and make an exhibition using their pictures. In the end of the project, students were instructed to fill in questionnaires to show their perception before and after the project. The result reveals that Cultural Snapshot Project has given the opportunity for the students to better realize cross-cultural understanding in their environment. In conclusion, the study shows that Cultural Snapshot Project has specifically enhanced students’ perception of multiculturalism in three major areas: cultural sensitivity and empathy, social tolerance, and understanding of diversity.

Keywords: cultural snapshot, cross-cultural understanding, students’ perception, multiculturalism

Procedia PDF Downloads 313

Authors: Paula Smith

Abstract:

During adolescence, many students engage in maladaptive behaviors that may reflect a lack of knowledge in social-emotional skills. Oftentimes these behaviors lead to conflicts and school-related disciplinary actions. Therefore, conflict resolution skills are vital for academic and social success. Conflict resolution is one component of a social-emotional learning (SEL) pedagogy that can effectively reduce discipline referrals and build students' social-emotional capacity. This action research study utilized a researcher-developed virtual SEL curriculum to provide instruction to eight adolescent students in an urban school in New York City with the goal of fostering their emotional intelligence (EI), reducing aggressive behaviors, and supporting instruction beyond the core academic content areas. Adolescent development, EI, and SEL frameworks were used to formulate this curriculum. Using a qualitative approach, this study inquired into how effectively participants responded to SEL instruction offered in virtual, Zoom-based workshops. Data included recorded workshop sessions, researcher field notes, and Zoom transcripts. Descriptive analysis involved manual coding/re-coding of transcripts to understand participants’ lived experience with conflict and the ideas presented in the workshops. Findings highlighted several themes and cultural norms that provided insight into adolescents' lived experiences and helped explain their past ideas about conflict. Findings also revealed participants' perspectives about the importance of SEL skills. This study illustrates one example of how evidence-based SEL programs might offer adolescents an opportunity to share their lived experiences. Programs such as this also address both individual and group needs, enabling practitioners to help students develop practical conflict resolution skills.

Keywords: social, emotional, learning, conflict, resolution

Procedia PDF Downloads 16

Authors: Yangzhi Li

Abstract:

Network transfer of information and performance customization is now a viable method of digital industrial production in the era of Industry 4.0. Robot platforms and network platforms have grown more important in digital design and construction. The pressing need for novel building techniques is driven by the growing labor scarcity problem and increased awareness of construction safety. Robotic approaches in construction research are regarded as an extension of operational and production tools. Several technological theories related to robot autonomous recognition, which include high-performance computing, physical system modeling, extensive sensor coordination, and dataset deep learning, have not been explored using intelligent construction. Relevant transdisciplinary theory and practice research still has specific gaps. Optimizing high-performance computing and autonomous recognition visual guidance technologies improves the robot's grasp of the scene and capacity for autonomous operation. Intelligent vision guidance technology for industrial robots has a serious issue with camera calibration, and the use of intelligent visual guiding and identification technologies for industrial robots in industrial production has strict accuracy requirements. It can be considered that visual recognition systems have challenges with precision issues. In such a situation, it will directly impact the effectiveness and standard of industrial production, necessitating a strengthening of the visual guiding study on positioning precision in recognition technology. To best facilitate the handling of complicated components, an approach for the visual recognition of parts utilizing machine learning algorithms is proposed. This study will identify the position of target components by detecting the information at the boundary and corner of a dense point cloud and determining the aspect ratio in accordance with the guidelines for the modularization of building components. To collect and use components, operational processing systems assign them to the same coordinate system based on their locations and postures. The RGB image's inclination detection and the depth image's verification will be used to determine the component's present posture. Finally, a virtual environment model for the robot's obstacle-avoidance route will be constructed using the point cloud information.

Keywords: robotic construction, robotic assembly, visual guidance, machine learning

Procedia PDF Downloads 86

Authors: Kemal Polat

Abstract:

In this paper, three feature weighting methods have been used to improve the classification performance of diabetic retinopathy (DR). To classify the diabetic retinopathy, features extracted from the output of several retinal image processing algorithms, such as image-level, lesion-specific and anatomical components, have been used and fed them into the classifier algorithms. The dataset used in this study has been taken from University of California, Irvine (UCI) machine learning repository. Feature weighting methods including the fuzzy c-means clustering based feature weighting, subtractive clustering based feature weighting, and Gaussian mixture clustering based feature weighting, have been used and compered with each other in the classification of DR. After feature weighting, five different classifier algorithms comprising multi-layer perceptron (MLP), k- nearest neighbor (k-NN), decision tree, support vector machine (SVM), and Naïve Bayes have been used. The hybrid method based on combination of subtractive clustering based feature weighting and decision tree classifier has been obtained the classification accuracy of 100% in the screening of DR. These results have demonstrated that the proposed hybrid scheme is very promising in the medical data set classification.

Keywords: machine learning, data weighting, classification, data mining

Procedia PDF Downloads 325

Authors: Dawood Al Chanti, Alice Caplier

Abstract:

Sparse representations of signals have received a great deal of attention in recent years. In this paper, the interest of using sparse representation as a mean for performing sparse discriminative analysis between spontaneous facial expressions is demonstrated. An automatic facial expressions recognition system is presented. It uses a KSVD-SVM approach which is made of three main stages: A pre-processing and feature extraction stage, which solves the problem of shared subspace distribution based on the random projection theory, to obtain low dimensional discriminative and reconstructive features; A dictionary learning and sparse coding stage, which uses the KSVD model to learn discriminative under or over dictionaries for sparse coding; Finally a classification stage, which uses a SVM classifier for facial expressions recognition. Our main concern is to be able to recognize non-basic affective states and non-acted expressions. Extensive experiments on the JAFFE static acted facial expressions database but also on the DynEmo dynamic spontaneous facial expressions database exhibit very good recognition rates.

Keywords: dictionary learning, random projection, pose and spontaneous facial expression, sparse representation

Procedia PDF Downloads 305

Authors: Yu-Chen Wei

Abstract:

The relationship between organizational human capital and organizational effectiveness have been a common topic of interest to organization researchers. Much of this research has concluded that higher human capital can predict greater organizational outcomes. Whereas human capital research has traditionally focused on organizations, the current study turns to the team level human capital. In addition, there are no known empirical studies assessing the effect of human capital divergence on team performance. Team human capital refers to the sum of knowledge, ability, and experience embedded in team members. Team human capital divergence is defined as the variation of human capital within a team. This study is among the first to assess the role of human capital divergence as a moderator of the effect of team human capital on team performance. From the traditional perspective, team human capital represents the collective ability to solve problems and reducing operational risk of all team members. Hence, the higher team human capital, the higher the team performance. This study further employs social learning theory to explain the relationship between team human capital and team performance. According to this theory, the individuals will look for progress by way of learning from teammates in their teams. They expect to have upper human capital, in turn, to achieve high productivity, obtain great rewards and career success eventually. Therefore, the individual can have more chances to improve his or her capability by learning from peers of the team if the team members have higher average human capital. As a consequence, all team members can develop a quick and effective learning path in their work environment, and in turn enhance their knowledge, skill, and experience, leads to higher team performance. This is the first argument of this study. Furthermore, the current study argues that human capital divergence is negative to a team development. For the individuals with lower human capital in the team, they always feel the pressure from their outstanding colleagues. Under the pressure, they cannot give full play to their own jobs and lose more and more confidence. For the smart guys in the team, they are reluctant to be colleagues with the teammates who are not as intelligent as them. Besides, they may have lower motivation to move forward because they are prominent enough compared with their teammates. Therefore, human capital divergence will moderate the relationship between team human capital and team performance. These two arguments were tested in 510 team-seasons drawn from major league baseball (1998–2014). Results demonstrate that there is a positive relationship between team human capital and team performance which is consistent with previous research. In addition, the variation of human capital within a team weakens the above relationships. That is to say, an individual working with teammates who are comparable to them can produce better performance than working with people who are either too smart or too stupid to them.

Keywords: human capital divergence, team human capital, team performance, team level research

Procedia PDF Downloads 240

Authors: Pei Yi Lin

Abstract:

Objective: The objective of this study is to use machine learning methods to build an early prediction classifier model for acute delirium to improve the quality of medical care for intensive care patients. Background: Delirium is a common acute and sudden disturbance of consciousness in critically ill patients. After the occurrence, it is easy to prolong the length of hospital stay and increase medical costs and mortality. In 2021, the incidence of delirium in the intensive care unit of internal medicine was as high as 59.78%, which indirectly prolonged the average length of hospital stay by 8.28 days, and the mortality rate is about 2.22% in the past three years. Therefore, it is expected to build a delirium prediction classifier through big data analysis and machine learning methods to detect delirium early. Method: This study is a retrospective study, using the artificial intelligence big data database to extract the characteristic factors related to delirium in intensive care unit patients and let the machine learn. The study included patients aged over 20 years old who were admitted to the intensive care unit between May 1, 2022, and December 31, 2022, excluding GCS assessment <4 points, admission to ICU for less than 24 hours, and CAM-ICU evaluation. The CAMICU delirium assessment results every 8 hours within 30 days of hospitalization are regarded as an event, and the cumulative data from ICU admission to the prediction time point are extracted to predict the possibility of delirium occurring in the next 8 hours, and collect a total of 63,754 research case data, extract 12 feature selections to train the model, including age, sex, average ICU stay hours, visual and auditory abnormalities, RASS assessment score, APACHE-II Score score, number of invasive catheters indwelling, restraint and sedative and hypnotic drugs. Through feature data cleaning, processing and KNN interpolation method supplementation, a total of 54595 research case events were extracted to provide machine learning model analysis, using the research events from May 01 to November 30, 2022, as the model training data, 80% of which is the training set for model training, and 20% for the internal verification of the verification set, and then from December 01 to December 2022 The CU research event on the 31st is an external verification set data, and finally the model inference and performance evaluation are performed, and then the model has trained again by adjusting the model parameters. Results: In this study, XG Boost, Random Forest, Logistic Regression, and Decision Tree were used to analyze and compare four machine learning models. The average accuracy rate of internal verification was highest in Random Forest (AUC=0.86), and the average accuracy rate of external verification was in Random Forest and XG Boost was the highest, AUC was 0.86, and the average accuracy of cross-validation was the highest in Random Forest (ACC=0.77). Conclusion: Clinically, medical staff usually conduct CAM-ICU assessments at the bedside of critically ill patients in clinical practice, but there is a lack of machine learning classification methods to assist ICU patients in real-time assessment, resulting in the inability to provide more objective and continuous monitoring data to assist Clinical staff can more accurately identify and predict the occurrence of delirium in patients. It is hoped that the development and construction of predictive models through machine learning can predict delirium early and immediately, make clinical decisions at the best time, and cooperate with PADIS delirium care measures to provide individualized non-drug interventional care measures to maintain patient safety, and then Improve the quality of care.

Keywords: critically ill patients, machine learning methods, delirium prediction, classifier model

Procedia PDF Downloads 75

Authors: Chandu Rathnayake, Isuri Anuradha

Abstract:

Early detection and accurate diagnosis of lung diseases play a crucial role in improving patient prognosis. However, conventional diagnostic methods heavily rely on subjective symptom assessments and medical imaging, often causing delays in diagnosis and treatment. To overcome this challenge, we propose a novel lung disease prediction system that integrates patient symptoms and X-ray images to provide a comprehensive and reliable diagnosis.In this project, develop a mobile application specifically designed for detecting lung diseases. Our application leverages both patient symptoms and X-ray images to facilitate diagnosis. By combining these two sources of information, our application delivers a more accurate and comprehensive assessment of the patient's condition, minimizing the risk of misdiagnosis. Our primary aim is to create a user-friendly and accessible tool, particularly important given the current circumstances where many patients face limitations in visiting healthcare facilities. To achieve this, we employ several state-of-the-art algorithms. Firstly, the Decision Tree algorithm is utilized for efficient symptom-based classification. It analyzes patient symptoms and creates a tree-like model to predict the presence of specific lung diseases. Secondly, we employ the Random Forest algorithm, which enhances predictive power by aggregating multiple decision trees. This ensemble technique improves the accuracy and robustness of the diagnosis. Furthermore, we incorporate a deep learning model using Convolutional Neural Network (CNN) with the RestNet50 pre-trained model. CNNs are well-suited for image analysis and feature extraction. By training CNN on a large dataset of X-ray images, it learns to identify patterns and features indicative of lung diseases. The RestNet50 architecture, known for its excellent performance in image recognition tasks, enhances the efficiency and accuracy of our deep learning model. By combining the outputs of the decision tree-based algorithms and the deep learning model, our mobile application generates a comprehensive lung disease prediction. The application provides users with an intuitive interface to input their symptoms and upload X-ray images for analysis. The prediction generated by the system offers valuable insights into the likelihood of various lung diseases, enabling individuals to take appropriate actions and seek timely medical attention. Our proposed mobile application has significant potential to address the rising prevalence of lung diseases, particularly among young individuals with smoking addictions. By providing a quick and user-friendly approach to assessing lung health, our application empowers individuals to monitor their well-being conveniently. This solution also offers immense value in the context of limited access to healthcare facilities, enabling timely detection and intervention. In conclusion, our research presents a comprehensive lung disease prediction system that combines patient symptoms and X-ray images using advanced algorithms. By developing a mobile application, we provide an accessible tool for individuals to assess their lung health conveniently. This solution has the potential to make a significant impact on the early detection and management of lung diseases, benefiting both patients and healthcare providers.

Keywords: CNN, random forest, decision tree, machine learning, deep learning

Procedia PDF Downloads 73

Authors: Paramvir Singh

Abstract:

The locomotion of aquatic organisms has long fascinated biologists and engineers alike, with fish fins serving as a prime example of nature's remarkable adaptations for efficient underwater propulsion. This paper presents a comprehensive study focused on the hydrodynamic analysis of fish fin kinematics, employing an innovative approach that combines machine learning and image processing techniques. Through high-speed videography and advanced computational tools, we gain insights into the complex and dynamic motion of the fins of a Tilapia (Oreochromis Niloticus) fish. This study was initially done by experimentally capturing videos of the various motions of a Tilapia in a custom-made setup. Using deep learning and image processing on the videos, the motion of the Caudal and Pectoral fin was extracted. This motion included the fin configuration (i.e., the angle of deviation from the mean position) with respect to time. Numerical investigations for the flapping fins are then performed using a Computational Fluid Dynamics (CFD) solver. 3D models of the fins were created, mimicking the real-life geometry of the fins. Thrust Characteristics of separate fins (i.e., Caudal and Pectoral separately) and when the fins are together were studied. The relationship and the phase between caudal and pectoral fin motion were also discussed. The key objectives include mathematical modeling of the motion of a flapping fin at different naturally occurring frequencies and amplitudes. The interactions between both fins (caudal and pectoral) were also an area of keen interest. This work aims to improve on research that has been done in the past on similar topics. Also, these results can help in the better and more efficient design of the propulsion systems for biomimetic underwater vehicles that are used to study aquatic ecosystems, explore uncharted or challenging underwater regions, do ocean bed modeling, etc.

Keywords: biomimetics, fish fin kinematics, image processing, fish tracking, underwater vehicles

Procedia PDF Downloads 89

Authors: Meenalochana Inguva

Abstract:

The context: The Center for Preparatory study is one of the strongest and most vibrant academic teaching units of the Sultan Qaboos University (SQU). The Foundation Programme English Language (FPEL) is part of a larger foundation programme which was implemented at SQU in fall 2010. The programme has been designed to prepare the students who have been accepted to study in the university in order to achieve the required educational goals (the learning outcomes) that have been designed according to Oman Academic Standards and published by the Omani Authority for Academic Accreditation (OAAA) for the English language component. The curriculum: At the CPS, the English language curriculum is based on the learning outcomes drafted for each level. These learning outcomes guide the students in meeting what is expected of them by the end of each level. These six levels are progressive in nature and are seen as a continuum. The study: A periodic evaluation of language programmes is necessary to improve the quality of the programmes and to meet the set goals of the programmes. An evaluation may be carried out internally or externally depending on the purpose and context. A self-study programme was initiated at the beginning of spring semester 2015 with a team comprising a total of 11 members who worked with-in the assigned course areas (level and programme specific). Only areas specific to FPEL have been included in the study. The study was divided into smaller tasks and members focused on their assigned courses. The self-study primarily focused on analyzing the programme LOs, curriculum planning, materials used and their relevance against the GFP exit standards. The review team also reflected on the assessment methods and procedures followed to reflect on student learning. The team has paid attention to having standard criteria for assessment and transparency in procedures. A special attention was paid to the staging of LOs across levels to determine students’ language and study skills ability to cope with higher level courses. Findings: The findings showed that most of the LOs are met through the materials used for teaching. Students score low on objective tests and high on subjective tests. Motivated students take advantage of academic support activities others do not utilize the student support activities to their advantage. Reading should get more hours. In listening, the format of the listening materials in CT 2 does not match the test format. Some of the course materials need revision. For e.g. APA citation, referencing etc. No specific time is allotted for teaching grammar Conclusion: The findings resulted in taking actions in bridging gaps. It will also help the center to be better prepared for the external review of its FPEL curriculum. It will also provide a useful base to prepare for the self-study portfolio for GFP standards assessment and future audit.

Keywords: curriculum planning, learning outcomes, reflections, self-evaluation

Procedia PDF Downloads 226

Authors: Yongjiang Zhang, Kallol Barai, Umesh R. Hodeghatta, Trang Tran, Vikas Dhiman

Abstract:

Detecting water stress on crops early and accurately is crucial to minimize its impact. This study aims to measure water stress in wild blueberry crops non-destructively by analyzing proximal hyperspectral data. The data collection took place in the summer growing season of 2022. A drought experiment was conducted on wild blueberries in the randomized block design in the greenhouse, incorporating various genotypes and irrigation treatments. Hyperspectral data ( spectral range: 400-1000 nm) using a handheld spectroradiometer and leaf water potential data using a pressure chamber were collected from wild blueberry plants. Machine learning techniques, including multiple regression analysis and random forest models, were employed to predict leaf water potential (MPa). We explored the optimal wavelength bands for simple differences (RY1-R Y2), simple ratios (RY1/RY2), and normalized differences (|RY1-R Y2|/ (RY1-R Y2)). NDWI ((R857 - R1241)/(R857 + R1241)), SD (R2188 – R2245), and SR (R1752 / R1756) emerged as top predictors for predicting leaf water potential, significantly contributing to the highest model performance. The base learner models achieved an R-squared value of approximately 0.81, indicating their capacity to explain 81% of the variance. Research is underway to develop a neural vegetation index (NVI) that automates the process of index development by searching for specific wavelengths in the space ratio of linear functions of reflectance. The NVI framework could work across species and predict different physiological parameters.

Keywords: hyperspectral reflectance, water potential, spectral indices, machine learning, wild blueberries, optimal bands

Procedia PDF Downloads 67

Authors: Matthew Armitt

Abstract:

The revolutionary school of architectural teaching – VKhUTEAMAS (1923-1926) was a new approach for a new society bringing architectural education to the masses and masses to the growing industrial production. The school's pedagogical contribution of the 1920s made it an important school of the modernist movement, engaging pedagogy as a mode of experimentation. The teachers and students saw design education not just as a process of knowledge transfer but as a vehicle for design innovation developing an approach without precedent. This process of teaching and learning served as a vehicle for venturing into the unknown through a discipline of architectural teaching called “Space” developed by the Soviet architect Nikolai Ladovskii (1881-1941). The creation of “Space” was paramount not only for its innovative pedagogy but also as an experimental laboratory for developing new architectural language. This paper discusses whether the historical teaching of “Space” can function in the construction of the modern teaching identity today to promote value, richness, quality, and diversity inherent in architectural design education. The history of “Space” teaching remains unknown within academic circles and separate from the current architectural teaching debate. Using VKhUTEMAS and the teaching of “Space” as a pedagogical lens and drawing upon research carried out in the Russian Federation, America, Canada, Germany, and the UK, this paper discusses how historically different models of teaching and learning can intersect through examining historical based educational research by exploring different design studio initiatives; pedagogical methodologies; teaching and learning theories and problem-based projects. There are strong arguments and desire for pedagogical change and this paper will promote new historical and educational research to widen the current academic debate by exposing new approaches to architectural teaching today.

Keywords: VKhUTEMAS, discipline space, modernist pedagogy, teaching identity

Procedia PDF Downloads 127

Authors: Hongmei Chi

Abstract:

The Blockchain has become a necessity for many different societal industries and ordinary lives including cryptocurrency technology, supply chain, health care, public safety, education, etc. Therefore, training our future blockchain developers to know blockchain programming vulnerability and I.T. students' cyber security is in high demand. In this work, we propose a framework including learning modules and hands-on labs to guide future I.T. professionals towards developing secure blockchain programming habits and mitigating source code vulnerabilities at the early stages of the software development lifecycle following the concept of Secure Software Development Life Cycle (SSDLC). In this research, our goal is to make blockchain programmers and I.T. students aware of the vulnerabilities of blockchains. In summary, we develop a framework that will (1) improve students' skills and awareness of blockchain source code vulnerabilities, detection tools, and mitigation techniques (2) integrate concepts of blockchain vulnerabilities for IT students, (3) improve future IT workers’ ability to master the concepts of blockchain attacks.

Keywords: software vulnerability detection, hands-on lab, static analysis tools, vulnerabilities, blockchain, active learning

Procedia PDF Downloads 99

Authors: Bhekisisa Nyoni, Nomakhosi Ndiweni, Annatoria Chinyama

Abstract:

The aim of this paper was to explore ways to enhance the quality of higher education with a bias towards engineering education in Zimbabwe universities. A search through relevant literature was conducted looking at both international and local scholars. It also involved reviewing the Dakar Framework for Action and Incheon Declaration and Framework for Action plans for education for sustainable development. Goals were set for 2030 as a standard for quality to be adopted by all countries in improving access as well as the quality of education from early childhood and through to adult learning. Despite the definition of quality being difficult to express due to diverse expectations from different stakeholders, the view of quality adopted is based on the World Education Forum’s propositions on quality education going beyond the classroom experience. It considers factors such as learning environment, governance and management, and teacher caliber. The study concludes by illustrating that the quality of engineering education in Zimbabwe has come a long way. It has made strides in increasing access and variety to education though at the expense of quality in its totality. To improve the quality of engineering education, programs have been introduced to promote the professionalism of lecturers, such as industrial secondment and professional development courses.

Keywords: engineering education, quality of education, professional development, industrial secondment

Procedia PDF Downloads 181

Authors: Ahmed Mohammed Omer Alghamdi

Abstract:

Since the COVID-19 pandemic started, a rapid, unexpected transition from face-to-face to virtual classroom (VC) teaching has involved several challenges and obstacles. However, there are also opportunities and thoughts that need to be examined and discussed. In addition, the entire world is witnessing that the teaching system and, more particularly, higher education institutes have been interrupted. To maintain the learning and teaching practices as usual, countries were forced to transition from traditional to virtual classes using various technology-based devices. In this regard, the Kingdom of Saudi Arabia (KSA) is no exception. Focusing on how the current situation has forced many higher education institutes to change to virtual classes may possibly provide a clear insight into adopted practices and implications. The main purpose of this study, therefore, was to investigate how both Saudi English as a foreign language (EFL) teachers and students perceived the implementation of virtual classes as a key factor for useful language teaching and learning process during the COVID-19 pandemic period at a Saudi university. The impetus for the research was, therefore, the need to find ways of identifying the deficiencies in this application and to suggest possible solutions that might rectify those deficiencies. This study seeks to answer the following overarching research question: “How do Saudi EFL instructors and students perceive the use of virtual classes during the COVID-19 pandemic period in their language teaching and learning context?” The following sub-questions are also used to guide the design of the study to answer the main research question: (1) To what extent are virtual classes important intra-pandemic from Saudi EFL instructors’ and students’ perspectives? (2) How effective are virtual classes for fostering English language students’ achievement? (3) What are the challenges and obstacles that instructors and students may face during the implementation of virtual teaching? A mixed method approach was employed in this study; the questionnaire data collection represented the quantitative method approach for this study, whereas the transcripts of recorded interviews represented the qualitative method approach. The participants included EFL teachers (N = 4) and male and female EFL students (N = 36). Based on the findings of this study, various aspects from teachers' and students’ perspectives were examined to determine the use of the virtual classroom applications in terms of fulfilling the students’ English language learning needs. The major findings of the study revealed that the virtual classroom applications during the current pandemic situation encountered three major challenges, among which the existence of the following essential aspects, namely lack of technology and an internet connection, having a large number of students in a virtual classroom and lack of students’ and teachers’ interactions during the virtual classroom applications. Finally, the findings indicated that although Saudi EFL students and teachers view the virtual classrooms in a positive light during the pandemic period, they reported that for long and post-pandemic period, they preferred the traditional face-to-face teaching procedure.

Keywords: virtual classes, English as a foreign language, COVID-19, Internet, pandemic

Procedia PDF Downloads 86

Authors: Rui Yin, Haojie Wang, Xun Li

Abstract:

Recently, mainstream dense retrieval methods have obtained state-of-the-art results on some datasets and tasks. However, they require large amounts of training data, which is not available in most domains. The severe performance degradation of dense retrievers on new data domains has limited the use of dense retrieval methods to only a few domains with large training datasets. In this paper, we propose an unsupervised domain-adaptive approach based on query generation. First, a generative model is used to generate relevant queries for each passage in the target corpus, and then, the generated queries are used for mining negative passages. Finally, the query-passage pairs are labeled with a cross-encoder and used to train a domain-adapted dense retriever. We also explore contrastive learning as a method for training domain-adapted dense retrievers and show that it leads to strong performance in various retrieval settings. Experiments show that our approach is more robust than previous methods in target domains that require less unlabeled data.

Keywords: dense retrieval, query generation, contrastive learning, unsupervised training

Procedia PDF Downloads 104

Authors: Güzi̇n Ti̇rkeş, Özge Teki̇n, Kerem Kurtuluş, Y. Yekta Yurtseven, Murat Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: convolutional neural networks, deep learning, image classification, scanning electron microscope

Procedia PDF Downloads 125

Authors: Maria Poulou

Abstract:

The study investigated how teachers’ self-rated Emotional Intelligence (EI), competence in implementing Social and Emotional Learning (SEL) skills and teaching efficacy relate to teacher-student relationships and students’ emotional and behavioral difficulties. Participants were 98 elementary teachers from public schools in central Greece. They completed the Self-Rated Emotional Intelligence Scale (SREIS), the Teacher SEL Beliefs Scale, the Teachers’ Sense of Efficacy Scale (TSES), the Student-Teacher Relationships Scale-Short Form (STRS-SF) and the Strengths and Difficulties Questionnaire (SDQ) for 617 of their students, aged 6-11 years old. Structural equation modeling was used to examine an exploratory model of the variables. It was demonstrated that teachers’ emotional intelligence, SEL beliefs and teaching efficacy were significantly related to teacher-student relationships, but they were not related to students’ emotional and behavioral difficulties. Rather, teachers’ perceptions of teacher-students relationships were significantly related to these difficulties. These findings and their implications for research and practice are discussed.

Keywords: emotional intelligence, social and emotional learning, teacher-student relationships, teaching efficacy

Procedia PDF Downloads 440

Authors: Ruwan Gunawardane

Abstract:

Second language teaching and learning is a complex process in which various factors are identified as having a negative impact on the competency in English among undergraduates of Sri Lanka. One such issue is the lack of intrinsic motivation among them to learn English despite the fact that they all know the importance of English. This study attempted to ascertain how the intrinsic motivation of undergraduates to learn English can be improved through reading out of curiosity. Humans are curious by nature, and cognitive psychology says that curiosity facilitates learning, memory, and motivation. The researcher carried out this study during the closure of universities due to the outbreak of the coronavirus through ‘Online Reading Café’, an online reading programme introduced by himself. He invited 1166 students of the Faculty of Science, University of Ruhuna, to read 50 articles taken from CNN and the BBC and posted at least two to three articles on the LMS of the faculty almost every day over a period of 23 days. The themes of the articles were based on the universe, exploration of planets, scientific experiments, evolution, etc., and the students were encouraged to collect as many words, phrases, and sentence structures as possible while reading and to form meaningful sentences using them. The data obtained through the students’ feedback was qualitatively analyzed. It was found that these undergraduates were interested in reading something out of curiosity, due to which intrinsic motivation is enhanced, and it facilitates competence in L2.

Keywords: English, competence, reading, curiosity

Procedia PDF Downloads 138

Authors: Tumelo Jaquiline Ntsopi

Abstract:

This study explored the academic writing challenges of first-year students who use English as an Additional Language (EAL) registered in the EAW101 module at an ODeL institution. Research shows that academic writing is a challenge for EAL teaching and learning contexts across the globe in higher education institutions (HEIs). Academic writing is an important aspect of academic literacy in any institution of higher learning, more so in an ODeL institution. This has probed research that shows that academic writing is and continues to pose challenges for EAL teaching and learning contexts in higher education institutions. This study stems from the researcher’s experience in teaching academic writing to first-year students in the EAW101 module. The motivation for this study emerged from the fact that EAW101 is a writing module that has a high number of students in the Department of English Studies with an average of between 50-80 percent pass rate. These statistics elaborate on the argument that most students registered in this module struggle with academic writing, and they need intervention to assist and support them in achieving competence in the module. This study is underpinned by Community of Inquiry (CoI) framework and Transactional distance theory. This study adopted a qualitative research methodology and utilised a case study approach as a research design. Furthermore, the study gathered data from first year students and the EAW101 module’s student support initiatives. To collect data, focus group discussions, structured open-ended evaluation questions, and an observation schedule were used to gather data. The study is vital towards exploring academic writing challenges that first-year students in EAW101 encounter so that lecturers in the module may consider re-evaluating their methods of teaching to improve EAL students’ academic writing skills. This study may help lecturers towards enhancing academic writing in a ODeL context by assisting first year students through using student support interventions.

Keywords: academic writing, academic writing challenge, ODeL, EAL

Procedia PDF Downloads 105