Search results for: indiana university dataset

Authors: Fawaz Saad, Hamid Alalwany

Abstract:

Sweden has succeeded to maintain a high level of growth and development and has managed to sustain highly ranked position among the world’s developed countries. In this regard, Swedish universities are playing a vital role in supporting innovation and entrepreneurship at all levels and developing Swedish knowledge economy. This paper is aiming to draw on the experiences of two leading Swedish universities, addressing their transformation approach to create entrepreneurial universities and fulfilling their objectives in the era of knowledge economy. The objectives of the paper include: (1) Introducing the Swedish higher education and its characteristics. (2) Examining the infrastructure elements for innovation and Entrepreneurship at two of the Swedish entrepre-neurial universities. (3) Addressing the key aspects of support systems in the initiatives of both Chalmers and Gothenburg universities to support innovation and advance entrepreneurial practices. The paper will contribute to two discourses: (1) Examining the relationship between support systems for innovation and entrepreneurship and the Universities’ policies and practices. (2) Lessons for University leaders to assist the development and implementation of effective innovation and en-trepreneurship policies and practices.

Keywords: Entrepreneurial University, Chalmers University, Gothenburg University, innovation and entrepreneurship policies, entrepreneurial transformation

Procedia PDF Downloads 503

Authors: Barbora Chmelíková

Abstract:

Making sound financial decisions is an essential skill which can have an impact on life of each consumer of financial products. The aim of this paper is to examine decision-making concerning financial matters and personal finance. The selected target group was university students majoring in finance related fields. The study was conducted in the Czech Republic at Masaryk University in 2015. In order to analyze financial decision-making questions related to basic finance decisions were developed to address the research objective. The results of the study suggest gaps in detecting best solutions to given financial decision-making questions among finance students. The analysis results indicate relation between financial decision-making and own experience with holding and using concrete financial products.

Keywords: financial decision-making, financial literacy, personal finance, university students

Procedia PDF Downloads 321

Authors: Beruk Berhanu Desalegn, Kebede Awgechew, Addisalem Mesfin

Abstract:

Introduction: This study aimed to investigate and compare the energy and selected nutrient intakes of sport science and non-sport science University students of Southern Ethiopia. Method: Multiple-day dietary data were collected from 166 university students (76 sport science and 90 non-sport sciences). Average daily energy and nutrient intake, and inadequate intakes were calculated using NutriSurvey (NS). Results: There were significant differences (p < 0.05) in the median intakes of energy, total carbohydrate, and vitamin B1 between female students from the sport science and non-sport science groups, but only the median intake of iron was significantly different (p < 0.05) between the male sport and non-sport science students’ group. The prevalence of inadequate intake of vitamin B1 were significantly (p<0.05) higher in the male and female from the non-sport science groups compared to the male and female students’ groups in the sport science, respectively. Whereas, the prevalence of inadequate iron intake by the male sport science students’ group was significantly (p<0.05) higher compared to their counterparts. Similarly, the prevalence of inadequate energy among the females from the sport science group was significantly (p<0.05) higher compared to the female students from the non-sport science department group. The prevalence of inadequate intakes of dietary energy, and the majority of the nutrients (protein, fat, vitamin A, B1, B2, and magnesium) were high (>50%) in selected University students. Conclusion: The energy and majority of nutrient intakes by the students in the selected universities of southern Ethiopia were sub-optimal. Therefore, activities that will improve the dietary intake of University students should include weekly meal plan revision considering their average recommended nutrient intake (RNI).

Keywords: dietary intake, sport science, University students, Ethiopia

Procedia PDF Downloads 77

Authors: G. S. Androulakis, G. Deli, M. Kaisari, N. Mihos

Abstract:

Teaching practices at the university level have changed and developed during the last decade. Implementation of inverted classroom method in secondary education consists of a well-formed basis for academic teachers. On the other hand, distance learning is a well-known field in education research and widespread as a method of teaching. Nonetheless, the new pandemic found many Universities all over the world unprepared, which made adaptations to new methods of teaching a necessity. In this paper, we analyze a model of an inverted university classroom in a distance learning context. Thus, the main purpose of our research is to investigate students’ difficulties as they transit to a new style of teaching and explore their learning development during a semester totally different from others. Our teaching experiment took place at the Business Administration department of the University of Patras, in the context of two courses: Calculus, a course aimed at first-year students, and Statistics, a course aimed at second-year students. Second-year students had the opportunity to attend courses in the university classroom. First-year students started their semester with distance learning. Using a comparative study of these two groups, we explored significant differences in students’ learning procedures. Focused group interviews, written tests, analyses of students’ dialogues were used in a mixed quantity and quality research. Our analysis reveals students’ skills, capabilities but also a difficulty in following, non-traditional style of teaching. The inverted classroom model, according to our findings, offers benefits in the educational procedure, even in a distance learning environment.

Keywords: distance learning, higher education, inverted classroom, mathematics teaching

Procedia PDF Downloads 125

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 45

Authors: Langa Hendrick Musawenkosi, Twala Bhekisipho

Abstract:

The success or failure of students is a concern for every academic institution, college, university, governments and students themselves. Several approaches have been researched to address this concern. In this paper, a view is held that when a student enters a university or college or an academic institution, he or she enters an academic environment. The academic environment is unique concept used to develop the solution for making predictions effectively. This paper presents a model to determine the propensity of a student to succeed or fail in the French South African Schneider Electric Education Center (FSASEC) at the Vaal University of Technology (VUT). The Decision Tree algorithm is used to implement the model at FSASEC.

Keywords: FSASEC, academic environment model, decision trees, k-nearest neighbor, machine learning, popularity index, support vector machine

Procedia PDF Downloads 197

Authors: Oladapo Tolulope Ibitoye

Abstract:

Neural networks have become prominent and widely engaged in algorithmic-based machine learning networks. They are perfect in solving day-to-day issues to a certain extent. Neural networks are computing systems with several interconnected nodes. One of the numerous areas of application of neural networks is object detection. This is a prominent area due to the coronavirus disease pandemic and the post-pandemic phases. Wearing a face mask in public slows the spread of the virus, according to experts’ submission. This calls for the development of a reliable and effective model for detecting face masks on people's faces during compliance checks. The existing neural network models for facemask detection are characterized by their black-box nature and large dataset requirement. The highlighted challenges have compromised the performance of the existing models. The proposed model utilized Faster R-CNN Model on Inception V3 backbone to reduce system complexity and dataset requirement. The model was trained and validated with very few datasets and evaluation results shows an overall accuracy of 96% regardless of skin tone.

Keywords: convolutional neural network, face detection, face mask, masked faces

Procedia PDF Downloads 62

Authors: Darshana Sharma

Abstract:

Distance Education has emerged as a viable alternative to serve the higher educational needs of the socially and economically disadvantaged people of the remote, rural areas of Jammu region. The University of Jammu is a National Accreditation, and Assessment Council accredited, A+ university and has been accorded graded autonomy by the University Grants Commission. It is a dual mode university offering academic programmes through the regular departments and through the Directorate of Distance Education. The Directorate of Distance Education, University of Jammu still uses printed study material as a mode of instructional delivery. The development of technologies has assured increased interaction and communication for distance learners throughout the distance open learning institutions. Though it is tempting and convenient to adopt technology already being used by others, it may not prove effective for the simple reason that two institutions may be unlike in some respect. The use of technology must be conceived in view of the needs of the learners; geographical socio-economic-cultural and technological contexts and financial, administrative and academic resources of the institution. Mobile learning (m-learning) is a novel approach to knowledge acquisition and dissemination and is gaining global attention. It has evolved as one of the useful channels of distance learning promoting interaction between learners and teachers. It is felt that the Directorate of Distance Education, University of Jammu also needs to adopt new technologies to provide more effective academic and information support to distance learners in order to keep them motivated and also to develop self-learning skills. The chief objective of the research on which this paper is based was to measure the opinion of the distance learners of the DDE, the University of Jammu about the merits of mobile learning. It also explores their preferences for implementing mobile learning. The survey research design of descriptive research has been used. The data was collected from 400 distance learners enrolled with undergraduate and post-graduate programmes using self-constructed questionnaire containing five-point Likert scale items arranging from strongly agree, agree, indifferent, disagree and strongly disagree. Percentages were used to analyze the data. The findings lead to conclude that mobile learning has a great potential for the DDE for reaching out to the rural, remotely located distance learners of the Jammu region and also to improve the teaching-learning environment. The paper also finds out the challenges in the implementation of mobile learning in the region and further makes suggestions for effective implementation of mobile learning in DDE, University of Jammu.

Keywords: directorate of distance education, mobile learning, national accreditation and assessment council, university of Jammu

Procedia PDF Downloads 122

Authors: Kenneth Fon Mbah, Arash Habibi Lashkari, Ali A. Ghorbani

Abstract:

Phishing e-mails are a security issue that not only annoys online users, but has also resulted in significant financial losses for businesses. Phishing advertisements and pornographic e-mails are difficult to detect as attackers have been becoming increasingly intelligent and professional. Attackers track users and adjust their attacks based on users’ attractions and hot topics that can be extracted from community news and journals. This research focuses on deceptive Phishing attacks and their variants such as attacks through advertisements and pornographic e-mails. We propose a framework called Phishing Alerting System (PHAS) to accurately classify e-mails as Phishing, advertisements or as pornographic. PHAS has the ability to detect and alert users for all types of deceptive e-mails to help users in decision making. A well-known email dataset has been used for these experiments and based on previously extracted features, 93.11% detection accuracy is obtainable by using J48 and KNN machine learning techniques. Our proposed framework achieved approximately the same accuracy as the benchmark while using this dataset.

Keywords: phishing e-mail, phishing detection, anti phishing, alarm system, machine learning

Procedia PDF Downloads 334

Authors: Devatha Kalyan Kumar, R. Poovarasan

Abstract:

In this paper, we have taken certain important factors and health parameters of diabetes patients especially among children by birth (pediatric congenital) where using the above three metrics methods we are going to assess the importance of each attributes in the dataset and thereby determining the most highly responsible and co-related attribute causing diabetics among young patients. We use cost optimization, control chart and Spearmen methodologies for the real-time application of finding the data efficiency in this diabetes dataset. The Spearmen methodology is the correlation methodologies used in software development process to identify the complexity between the various modules of the software. Identifying the complexity is important because if the complexity is higher, then there is a higher chance of occurrence of the risk in the software. With the use of control; chart mean, variance and standard deviation of data are calculated. With the use of Cost optimization model, we find to optimize the variables. Hence we choose the Spearmen, control chart and cost optimization methods to assess the data efficiency in diabetes datasets.

Keywords: correlation, congenital diabetics, linear relationship, monotonic function, ranking samples, pediatric

Procedia PDF Downloads 252

Authors: Tahir Nawaz Cheema, Dumitru Baleanu, Ali Raza

Abstract:

In this research work, we design intelligent computing through Bayesian Regularization artificial neural networks (BRANNs) introduced to solve the mathematical modeling of infectious diseases (Covid-19). The dynamical transmission is due to the interaction of people and its mathematical representation based on the system's nonlinear differential equations. The generation of the dataset of the Covid-19 model is exploited by the power of the explicit Runge Kutta method for different countries of the world like India, Pakistan, Italy, and many more. The generated dataset is approximately used for training, testing, and validation processes for every frequent update in Bayesian Regularization backpropagation for numerical behavior of the dynamics of the Covid-19 model. The performance and effectiveness of designed methodology BRANNs are checked through mean squared error, error histograms, numerical solutions, absolute error, and regression analysis.

Keywords: mathematical models, beysian regularization, bayesian-regularization backpropagation networks, regression analysis, numerical computing

Procedia PDF Downloads 137

Authors: Syahruddin Sumardi, Indra Fajar Alamsyah, Junaidah Hashim

Abstract:

This study attempts to explore and presents a proposed recruitment model in Islamic university which aligned with holistic role. It is a conceptual paper in nature. In turn, this study is designed to utilize exploratory approach. Literature and document review that related to this topic are used as the methods to analyse the content found. Recruitment for any organization is fundamental to achieve its goal effectively. Staffing in universities is vital due to the importance role of lecturers. Currently, Islamic universities still adopt the common process of recruitment for their academic staffs. Whereas, they have own characteristics which are embedded in their institutions. Furthermore, the FCWC (Foundation, Capability, Worldview and Commitment) model of recruitment proposes to suit the holistic character of Islamic university. Further studies are required to empirically validate the concept through systematic investigations. Additionally, measuring this model by a designed means is appreciated. The model provides the map and alternative tool of recruitment for Islamic universities to determine the process of recruitment which can appropriate their institutions. In addition, it also allows stakeholders and policy makers to consider regarding Islamic values that should inculcate in the Islamic higher learning institutions. This study initiates a foundational contribution for an early sequence of research.

Keywords: academic staff, Islamic values, recruitment model, university

Procedia PDF Downloads 163

Authors: Nasir Umar Abdullahi

Abstract:

The social media profoundly causes the reading culture to decline in Nigeria, where the English language is a second language (SL), a language of instruction (LI), as well as the target language (TL). This is because the university students have, over the years, failed to make extensive reading their closest companion, with much emphasis on reading the European novels, newspapers, magazines, etc., so as to learn language from its original or native speakers for linguistic competence. Instead, they squander the most part of their day and nocturnal hours, sending and receiving messages through social media. The end result is their vocabulary become stagnant or ebbs, and that they cannot acquire the Cox head’s 570 vocabulary, let alone the Nation’s 2000 vocabulary to use the language fluently in writing, reading, listening, and speaking and to further compete with the native speaker in varying degrees of language usages. Be that as it may, if the social media is a monster in worsening the decline in reading culture, which degenerates in the Northern part of the country in contradistinction to the Southern part, it boosts it as well, for aside the social media language, slangs, cliché, for instance, students improve their vocabulary power, and at the same time it allows the students to privately and leisurely put the language into use, by using practically some of the vocabulary they have acquired to chart, to comment, socialize to adjudge, etc. This is what this paper tries to explore in Umaru Musa Yar’adua University Al-qalam University and the Federal University Dutin-ma.

Keywords: social media, reading, vocabulary, universities

Procedia PDF Downloads 126

Authors: Sandra Thompson, Paul Dervan

Abstract:

Ireland’s first Technological University (TU Dublin) was established on 1st January 2019, and its creation is an exciting new milestone in Irish Higher Education. TU Dublin is now Ireland’s biggest University supporting 29,000 students across three campuses with 3,500 staff. The University aspires to create work-ready graduates who are socially responsible, open-minded global thinkers who are ambitious to change the world for the better. As graduates, they will be enterprising and daring in all their endeavors, ready to play their part in transforming the future. Feedback from Irish employers and students coupled with evidence from other authoritative sources such as the World Economic Forum points to a need for greater focus on the development of students’ employability skills as they prepare for today’s work environment. Moreover, with an increased focus on Universal Design for Learning (UDL) and inclusiveness, there is recognition that students are more than a numeric grade value. Robust grading systems have been developed to track a student’s performance around discipline knowledge but there is little or no global consensus on a definition of transversal skills nor on a unified framework to assess transversal skills. Education and industry sectors are often assessing one or two skills, and some are developing their own frameworks to capture the learner’s achievement in this area. Technological University Dublin (TU Dublin) have discovered and implemented a framework to allow students to develop, assess and record their transversal skills using transformative learning theory. The model implemented is an adaptation of Student Transformative Learning Record - STLR which originated in the University of Central Oklahoma (UCO). The purpose of this paper therefore, is to examine the views of students, staff and employers in the context of deploying a Transformative Learning model within the University to assess transversal skills. It will examine the initial impact the transformative learning model is having socially, personally and on the University as an organization. Crucially also, to identify lessons learned from the deployment in order to assist other Universities and Higher Education Institutes who may be considering a focused adoption of Transformative Learning to meet the challenge of preparing students for today’s work environment.

Keywords: assessing transversal skills, higher education, transformative learning, students

Procedia PDF Downloads 126

Authors: Usiobaifo Agharese Rosemary, Osaseri Roseline Oghogho

Abstract:

Diabetes is a complex group of disease with a variety of causes; it is a disorder of the body metabolism in the digestion of carbohydrates food. The application of machine learning in the field of medical diagnosis has been the focus of many researchers and the use of recognition and classification model as a decision support tools has help the medical expert in diagnosis of diseases. Considering the large volume of medical data which require special techniques, experience, and high diagnostic skill in the diagnosis of diseases, the application of an artificial intelligent system to assist medical personnel in order to enhance their efficiency and accuracy in diagnosis will be an invaluable tool. In this study will propose a diabetes diagnosis model using rough set and K-nearest Neighbor classifier algorithm. The system consists of two modules: the feature extraction module and predictor module, rough data set is used to preprocess the attributes while K-nearest neighbor classifier is used to classify the given data. The dataset used for this model was taken for University of Benin Teaching Hospital (UBTH) database. Half of the data was used in the training while the other half was used in testing the system. The proposed model was able to achieve over 80% accuracy.

Keywords: classifier algorithm, diabetes, diagnostic model, machine learning

Procedia PDF Downloads 332

Authors: Yousra Drissi

Abstract:

This research explores language teacher identity in a multilingual context where both teachers and students come from different linguistic backgrounds. It seeks to understand how teachers perceive themselves as language teachers in this context in relation to different influencing factors, both internal and external. This study is being conducted due to the importance of language teacher identity (LTI) in the university context, which is being neglected in the present literature (in an attempt to address the gap in the present literature). The broader aim of this study is to bring attention to language teacher identity along with the different influencing elements which can either promote or hinder its development. In this research, we are using the sociocultural theory and post-structural theory. This research uses the mixed methods approach to collect and analyse relevant data. A structured survey was distributed to language teachers from different universities around Algeria, followed by in-depth interviews. Results are supposed to show the different points in self-perception that these teachers share or differ in. they will also help us identify the different internal and external factors that can be of influence. However, the results of this research can be used by institutions as well as decision-makers to better understand university teachers and help them improve their teaching practices by empowering their language teacher identity, starting from teacher education programs to continuous teacher development programs.

Keywords: identity, language teacher identity, multilingualism, university teacher

Procedia PDF Downloads 72

Authors: Marzena Świgoń

Abstract:

Nowadays, graduates should be prepared for serious challenges in the internal and external labor market. The notion that a degree is a “passport to employment” has been relegated to the past. In the last few years a phenomenon in the form of the increasing unemployment of highly educated young people in EU countries, including Poland has been observed. Empirical studies were conducted among Polish students in the scope of the so-called self-perceived employability review. In this study, a special scale was used which consisted of 19 statements regarding five components: student’s perception of university; field of study; self-belief; state of the external labor market; and, personal knowledge management. The respondent group consisted of final-year master’s students of International Relations at the University of Warmia and Mazury in Olsztyn, Poland. The findings of the empirical studies were compiled using statistical methods: descriptive statistics and inferential statistics. In general, in light of the conducted studies, the self-perceived employability of the Polish students was not high. Limitations of the studies were discussed, as well as the implications for future research in the scope of the students’ employability.

Keywords: self-perceived employability, students of international relations, university students, students employability

Procedia PDF Downloads 331

Authors: Thossaporn Thossansin

Abstract:

This paper presents the developing of a mobile application for students who are studying in a Faculty of Information Technology, Rangsit University (RSU), Thailand. RSU enhanced the enrollment process by leveraging its information systems, which allows students to download RSU APP. This helps students to access RSU’s information that is important for them. The reason to have a mobile application is to give support students’ ability to access the system at anytime, anywhere and anywhere. The objective of this paper was to develop an application on iOS platform for students who are studying in Faculty of Information Technology, Rangsit University, Thailand. Studies and learns student’s perception for a new mobile app. This paper has targeted a group of students who is studied in year 1-4 in the faculty of information technology, Rangsit University. This new application has been developed by the department of information technology, Rangsit University and it has generally called as RSU APP. This is a new mobile application development for RSU, which has useful features and functionalities in giving support to students. The core module has consisted of RSU’s announcement, calendar, event, activities, and ebook. The mobile app has developed on iOS platform that is related to RSU’s policies in giving free Tablets for the first year students. The user satisfaction is analyzed from interview data that has 81 interviews and Google application such as google form is taken into account for 122 interviews. Generally, users were satisfied to-use application with the most satisfaction at the level of 4.67. SD is 0.52, which found the most satisfaction in that users can learn and use quickly. The most satisfying is 4.82 and SD is 0.71 and the lowest satisfaction rating in its modern form, apps lists. The satisfaction is 4.01, and SD is 0.45.

Keywords: mobile application, development of mobile application, framework of mobile development, software development for mobile devices

Procedia PDF Downloads 319

Authors: Islam Elsayed Hussein

Abstract:

The aim of this paper is to discover the impact of students’ attitude towards social media and the skills required to adopt social media as a university e-learning (2.0) platform. In addition, it measures the effect of social media adoption on interactive learning effectiveness. The population of this study was students at Faculty of tourism and Hotels, Fayoum University. A questionnaire was used as a research instrument to collect data from respondents, which had been selected randomly. Data had been analyzed using quantitative data analysis method. Findings showed that the students have a positive attitude towards adopting social networking in the learning process and they have also good skills for effective use of social networking tools. In addition, adopting social media is effectively affecting the interactive learning environment.

Keywords: attitude, skills, e-learning 2.0, interactive learning, Egypt

Procedia PDF Downloads 517

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.

Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence

Procedia PDF Downloads 75

Authors: Gaelle Candel, David Naccache

Abstract:

t-SNE is an embedding method that the data science community has widely used. It helps two main tasks: to display results by coloring items according to the item class or feature value; and for forensic, giving a first overview of the dataset distribution. Two interesting characteristics of t-SNE are the structure preservation property and the answer to the crowding problem, where all neighbors in high dimensional space cannot be represented correctly in low dimensional space. t-SNE preserves the local neighborhood, and similar items are nicely spaced by adjusting to the local density. These two characteristics produce a meaningful representation, where the cluster area is proportional to its size in number, and relationships between clusters are materialized by closeness on the embedding. This algorithm is non-parametric. The transformation from a high to low dimensional space is described but not learned. Two initializations of the algorithm would lead to two different embeddings. In a forensic approach, analysts would like to compare two or more datasets using their embedding. A naive approach would be to embed all datasets together. However, this process is costly as the complexity of t-SNE is quadratic and would be infeasible for too many datasets. Another approach would be to learn a parametric model over an embedding built with a subset of data. While this approach is highly scalable, points could be mapped at the same exact position, making them indistinguishable. This type of model would be unable to adapt to new outliers nor concept drift. This paper presents a methodology to reuse an embedding to create a new one, where cluster positions are preserved. The optimization process minimizes two costs, one relative to the embedding shape and the second relative to the support embedding’ match. The embedding with the support process can be repeated more than once, with the newly obtained embedding. The successive embedding can be used to study the impact of one variable over the dataset distribution or monitor changes over time. This method has the same complexity as t-SNE per embedding, and memory requirements are only doubled. For a dataset of n elements sorted and split into k subsets, the total embedding complexity would be reduced from O(n²) to O(n²=k), and the memory requirement from n² to 2(n=k)², which enables computation on recent laptops. The method showed promising results on a real-world dataset, allowing to observe the birth, evolution, and death of clusters. The proposed approach facilitates identifying significant trends and changes, which empowers the monitoring high dimensional datasets’ dynamics.

Keywords: concept drift, data visualization, dimension reduction, embedding, monitoring, reusability, t-SNE, unsupervised learning

Procedia PDF Downloads 140

Authors: John Ayisi, Gideon M. Kivengea, George A. Ombakho

Abstract:

In this emerging era of knowledge economy, universities, as major centres of learning and research, are becoming increasingly important as sources of ideas, knowledge, skills, innovation and technological advances. These ideas can be turned into new products, processes and systems needed to drive their respective national economies, and thus placing universities at the centre of the national innovation systems. Thus, commercialization of research outputs from universities to industry has become an area of strong policy interest in African countries. To assess the level of commercialization of research outputs in Kenyan universities, a standardized questionnaire covering seven sub-sections, namely: University Commercialization Environment, Management of Commercialization Activities, Commercialization Office, Intellectual Property Rights (IPRs), Early Stage Financing and Venture Capital; Industrial Linkages; and Technology Parks and Incubators was administered among a few selected public and private universities. Results show that all the universities have a strategic plan; though not all have innovation and commercialization as part of it. Half the nineteen surveyed universities indicated they have created designated offices for fostering commercialization. Majority have guidelines on IPRs which advocate IP to be co-owned by researcher/university. University-industry linkages are weak. Most universities are taking precursory steps to incentivise and encourage entrepreneurial activities among their academic staff and students, even though the level of resources devoted to them is low. It is recommended that building capacity in entrepreneurship among staff and students and committing more resources to R&D activities hold potential to increased commercialization of university research outputs.

Keywords: commercialization, knowledge, R&D, university

Procedia PDF Downloads 436

Authors: Atuhurra Jesse, N'guessan Yves-Roland Douha, Pabitra Lenka

Abstract:

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, image classifiers to detect CSSVD-infected cacao plants are presented in this study. The classifiers are based on VGG16, ResNet50 and Vision Transformer (ViT). The image classifiers are evaluated on a recently released and publicly accessible KaraAgroAI Cocoa dataset. The best performing image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. These results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.

Keywords: CSSVD, image classification, ResNet50, vision transformer, KaraAgroAI cocoa dataset

Procedia PDF Downloads 96

Authors: Nutcha Taneepanichskul, Helen C. Hailes, Mark Miodownik

Abstract:

Plastic waste has emerged as a critical global environmental challenge, primarily driven by the prevalent use of conventional plastics derived from petrochemical refining and manufacturing processes in modern packaging. While these plastics serve vital functions, their persistence in the environment post-disposal poses significant threats to ecosystems. Addressing this issue necessitates approaches, one of which involves the development of biodegradable plastics designed to degrade under controlled conditions, such as industrial composting facilities. It is imperative to note that compostable plastics are engineered for degradation within specific environments and are not suited for uncontrolled settings, including natural landscapes and aquatic ecosystems. The full benefits of compostable packaging are realized when subjected to industrial composting, preventing environmental contamination and waste stream pollution. Therefore, effective sorting technologies are essential to enhance composting rates for these materials and diminish the risk of contaminating recycling streams. In this study, it leverage hyperspectral imaging technology (HSI) coupled with advanced machine learning algorithms to accurately identify various types of plastics, encompassing conventional variants like Polyethylene terephthalate (PET), Polypropylene (PP), Low density polyethylene (LDPE), High density polyethylene (HDPE) and biodegradable alternatives such as Polybutylene adipate terephthalate (PBAT), Polylactic acid (PLA), and Polyhydroxyalkanoates (PHA). The dataset is partitioned into three subsets: a training dataset comprising uncontaminated conventional and biodegradable plastics, a validation dataset encompassing contaminated plastics of both types, and a testing dataset featuring real-world packaging items in both pristine and contaminated states. Five distinct machine learning algorithms, namely Partial Least Squares Discriminant Analysis (PLS-DA), Support Vector Machine (SVM), Convolutional Neural Network (CNN), Logistic Regression, and Decision Tree Algorithm, were developed and evaluated for their classification performance. Remarkably, the Logistic Regression and CNN model exhibited the most promising outcomes, achieving a perfect accuracy rate of 100% for the training and validation datasets. Notably, the testing dataset yielded an accuracy exceeding 80%. The successful implementation of this sorting technology within recycling and composting facilities holds the potential to significantly elevate recycling and composting rates. As a result, the envisioned circular economy for plastics can be established, thereby offering a viable solution to mitigate plastic pollution.

Keywords: biodegradable plastics, sorting technology, hyperspectral imaging technology, machine learning algorithms

Procedia PDF Downloads 75

Authors: Gabriele Borg, Alexei Debono, Charlie Abela

Abstract:

There on a constant rise in the availability of high volumes of data gathered from multiple sources, resulting in an abundance of unprocessed information that can be used to monitor patterns and trends in user behaviour. Similarly, year after year, Malta is also constantly experiencing ongoing population growth and an increase in mobilization demand. This research takes advantage of data which is continuously being sourced and converting it into useful information related to the traffic problem on the Maltese roads. The scope of this paper is to provide a methodology to create a custom dataset (MalTra - Malta Traffic) compiled from multiple participants from various locations across the island to identify the most common routes taken to expose the main areas of activity. This use of big data is seen being used in various technologies and is referred to as ITSs (Intelligent Transportation Systems), which has been concluded that there is significant potential in utilising such sources of data on a nationwide scale. Furthermore, a series of traffic prediction graph neural network models are conducted to compare MalTra to large-scale traffic datasets.

Keywords: graph neural networks, traffic management, big data, mobile data patterns

Procedia PDF Downloads 123

Authors: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 62

Authors: D. S. Denchuk, O. M. Zamyatina, M. G. Minin, M. A. Soloviev, K. V. Bogrova

Abstract:

The article considers invention activity in Russia and worldwide, its modern state, and the impact of innovative engineering activity on the national economy of the considered countries. It also analyses the historical premises of modern engineer-ing invention. The authors explore the development of engineering invention at an engineer-ing university, the creation of particular environment for scientific and technical creativity of students on the example of Elite engineering education program at Tomsk Polytechnic University, Russia. It is revealed that for the successful de-velopment of engineering invention in a higher education institution it is neces-sary to apply a learning model that develops the creative potential of a student, which is, in its turn, inseparably connected with the ability to generate new ideas in engineering. Such academic environment can become a basis for revealing stu-dents' creativity.

Keywords: engineering invention, scientific and technical creativity, students, project-based approach

Procedia PDF Downloads 387

Authors: Jovanca Smith, Derek Gay

Abstract:

All universities possess a standard by which students are assessed and administered into their programs. This paper considers the effect of the educational history of students, as measured by specific subject grades in Caribbean examinations, on overall performance in introductory engineering math and mechanics courses. Results reflect a correlation between the highest grade in the Caribbean examinations with a higher probability of successful advancement in the university courses. Alternatively, lower entrance grades are commensurate with underperformance in the university courses. Results also demonstrate that students matriculating with the Caribbean examinations will not necessarily possess a significant advantage over students entering through an alternative route, and while previous educational background of students is a significant indicator of tentative performance in the University level math and mechanics courses, it is not the sole factor.

Keywords: bimodal distribution, differential learning, engineering education, entrance qualification

Procedia PDF Downloads 359

Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen

Abstract:

Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.

Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques

Procedia PDF Downloads 96

Authors: Nopadol Burananat, Kedsara Tripaichayonsak

Abstract:

This research aims to study the level of expectations and participation of personnel in implementing educational quality assurance of programs in Graduate School, Rajabhat Suan Sunandha University. The sample used in this study is 60 participants. The tool used for data collection is a questionnaire constructed by the researcher. The analysis is done by frequency, percentage, mean and standard deviation. It was found that the level of expectations personnel in Graduate School, Suan Sunandha Rajabhat University in implementing educational quality assurance is at high level. The category which received the most score is Action, followed by Check, Do and Plan, respectively. For the level of participation of personnel at program level of Graduate School, Suan Sunandha Rajabhat University in implementing educational quality assurance, the overall score is at high level. The category which received the most score is Action, followed by Do, Check and Plan, respectively.

Keywords: participation, implementation of educational quality assurance, educational quality assurance, expectations and participation

Procedia PDF Downloads 381