133 research outputs found
Optimising iCadet Assignment through User Profiling
Get PDFIndustry Cadetship programme is a programme that assigns penultimate year students to companies matching their profiles, bridging academic learning and industry skills. Manual data analysis for assignments is time-intensive, prompting this study’s objectives: (i) propose an algorithm to optimize student-company assignment by using the student and company profiles, (ii) propose a method for the assignment of lecturers to company, and (iii) use similarity measure techniques to recommend companies with similar characteristics. Data was collected from a university's student, company, and lecturer datasets. To assign students to companies, the Haversine, OpenStreetMap, and NetworkX were used to calculate the shortest geographical distance between the students and the companies; evaluated based on mean, variance, standard deviation, and utilization rate. For the lecturer assignment, cosine similarity was applied to measure the similarity between domain descriptions and company or lecturer information after performing Voyage AI embeddings. Lecturers are assigned to companies based on the highest domain similarity scores. The performance was evaluated using accuracy, precision, recall, and F1- score. Findings showed embedding techniques significantly enhanced the matching process, with accuracy improved from 0.464 to 0.6071, precision increased from 0.417 to 0.5058, recall saw an equal rise from 0.464 to 0.6071, and the F1-score advanced from 0.417 to 0.5264. Longer descriptive inputs further improved performance, with accuracy rising from 0.6154 to 0.7692, precision from 0.5744 to 0.7751, recall remaining steady at 0.7692, and F1-score increasing from 0.5807 to 0.7484. This work can be extended to explore job portal dataset by aligning profiles with geography and specialization
Decision-Theoretic Approach To Designing Scientific Inquiry Based Learning Environment
No full textThe thesis focuses on developing a learner model for INQUIRY PROCESS(INQPRO), a scientific inquiry learning environment developed within this research work
Pembinaan perisian prototaip 'Sciencepro' berasaskan model inkuiri saintifik bagi mengkaji corak penyelesaian masalah pelajar melalui pembentukan hipotesis dan pengenalpastian pembolehubah bagi beberapa konsep fizik
No full textDigital Click Stream Data for Airline Seat Sale Prediction using GBT
No full textRevenue Management is important for every airline
business and the seat is the main product of an airline.
The purpose of the revenue management is to maximize
the revenue of each airline routes based on demand.
This demand, however, depends on factors such as
historical demand, seasonality, seat pricing based on
purchase lead days, competitors pricing and customer
behaviour. Prediction of passenger demand helps to
forecast revenue on future flights and thus allow the
airline to generate optimal prices for the corresponding
flights. Therefore, minimizing the prediction error
constitute the most crucial goal of good revenue
management. In this paper, A GBT based model has
been proposed for airline seat sale prediction to
optimize the revenue. To optimize the prediction
accuracy, an analytic dataset has been developed by
combining digital attributes and traditional operational
and transactional attributes. This paper will also
highlight an efficient data extraction and processing
pipeline have been proposed to aggregate a large
volume of unstructured data from various data sources.
The empirical findings suggested applying GBT on
transformed dataset can predi
Properties of Bayesian student model for INQPRO
No full textEmploying a probabilistic student model in a scientific inquiry learning environment often presents two challenges. First, what constitute the appropriate variables for modeling scientific inquiry skills in such a learning environment, considering the fact that it practices exploratory learning approach? Following exploratory learning approach, students are granted the freedom to navigate from one GUI to another. Second, do causal dependencies exist between the identified variables, and if they do, how should they be defined? To tackle the challenges, this research work attempted the Bayesian Networks framework. Leveraging on the framework, two student models were constructed to predict the acquisition of scientific inquiry skills for INQPRO, a scientific inquiry learning environment developed in this research work. The student models can be differentiated by the variables they modeled and the causal dependencies they encoded. An on-field evaluation involving 101 students was performed to assess the most appropriate structure of the INQPRO's student model. To ensure fairness in model comparison, the same Dynamic Bayesian Network (DBN) construction approach was employed. Lastly, this paper highlights the properties of the student model that provide optimal results for modeling scientific inquiry skill acquisition in INQPRO
Detecting Need-Attention Patients using Machine Learning
Get PDFIn healthcare, detecting patients who need immediate attention is difficult. Identifying the critical variables is challenging in patient detection because human intervention in variable selection is required. Consequently, patients who need immediate attention often experience prolonged waiting times. Researchers have investigated various approaches to identify those who require attention. One of the techniques is leveraging Artificial Intelligence (AI). However, identifying the optimal feature set and predictive model is complex. Therefore, this study has attempted to (i) identify the critical features and (ii) develop and evaluate predictive models in detecting those who need attention. The dataset is collected from one of the healthcare companies. The dataset collected contains 67 variables and 51102 records. It consists of patient information and questionnaires answered by each participant registered in the Selangor Saring Program. Important features were identified in detecting those who need attention on treated data. Multiple classifiers were developed due to their simplicity. The models were evaluated before and after hyperparameter tuning based on accuracy, precision, recall, F1-score, Geometric Mean, and Area Under the Curve. The findings showed that the Stacking Classifier produced the highest accuracy (69.9%) when using the blood dataset. In contrast, Extreme Gradient Boosting achieved the highest accuracy (81.7%) when the urine dataset was used. This work can be extended to explore the incorporation of Points of Interest and geographical data near patients’ residences and study other ensemble models to enhance the performance of detecting those who need attention
Assessing learner's Scientific Inquiry Skills across time: A Dynamic Bayesian Network approach
No full textIn this article, we develop and evaluate three Dynamic Bayesian Network (DBN) models for assessing temporally variable learner scientific inquiry skills (Hypothesis Generation and Variable Identification) in INQPRO learning environment. Empirical studies were carried out to examine the matching accuracies and identify the models' drawbacks. We demonstrate how the insights gained from a preceding model have eventually led to the improvement of subsequent models. In this study, the entire evaluation process involved 6 domain experts and 61 human learners. The matching accuracies of the models are measured by (1) comparing with the results gathered from the pretest, posttest, and learner's self-rating scores; and (2) comments given by domain experts based on learners' interaction logs and the graph patterns exhibited by the models
Scheduling and Predictive Maintenance for Smart Toilet
No full textModern society needs bathrooms. Poor sanitation is caused by worn-out appliances and expensive cleaning. The technique also requires an inexpensive, dependable sensor. This study had three goals. Creating an IoT administration platform is the main goal. Literature evaluations assess the merits and downsides of existing systems. Second, we suggest predictive maintenance to assist predict bathroom equipment breakdowns. Finally, a scheduling algorithm was used to determine how many janitors to hire. We’ll measure the model’s effectiveness and make future recommendations. Infrared, temperature and humidity sensors create an IoT bathroom. Sensors have been studied to understand how to adapt them to the hygienic and private toilet environment. Sensor accuracy and cost-effectiveness could be enhanced with more development and testing. The Auto-Regressive Integrated Moving Average (ARIMA) model accurately predicts time series lags, making it a good candidate for predictive maintenance. Long Short-Term Memory (LSTM) is good in time series predictions, therefore it’s fair to compare the two. We use the ARIMA model to handle Remaining Useful Life (RUL) prediction techniques by altering Moving Average (MA) and Auto-Regressive (AR). A genetic algorithm is used to create a janitorial cleaning schedule. The genetic algorithm was proposed to schedule cleaning workers. This approach improves the genetic algorithm by studying soft and hard scheduling restrictions. The Greedy algorithm is used to compare. Experimental evaluations reveal that the suggested model ARIGA meets both goals
A Bayesian approach to classify conference papers
No full textThis article aims at presenting a methodological approach for classifying educational conference papers by employing a Bayesian Network (BN). A total of 400 conference papers were collected and categorized into 4 major topics (Intelligent Tutoring System, Cognition, e-Learning, and Teacher Education). In this study, we have implemented a 80-20 split of collected papers. 80% of the papers were meant for keywords extraction and BN parameter learning whereas the other 20% were aimed for predictive accuracy performance. A feature selection algorithm was applied to automatically extract keywords for each topic. The extracted keywords were then used for constructing BN. The prior probabilities were subsequently learned using the Expectation Maximization (EM) algorithm. The network has gone through a series of validation by human experts and experimental evaluation to analyze its predictive accuracy. The result has demonstrated that the proposed BN has outperformed Naive Bayesian Classifier, and BN learned from the training data
Conceptual change modeling using Dynamic Bayesian network
No full textModeling the process of conceptual change in scientific inquiry learning environments involves uncertainty inherent in inferring learner's mental models. INQPRO, an intelligent scientific inquiry exploratory learning environment, refers to a probabilistic learner model aims at modeling conceptual change through the interactions with INQPRO Graphical User Interface (GUI) and Intelligent Pedagogical Agent. In this article, we first discuss how conceptual change framework can be integrated into scientific inquiry learning environment. Secondly, we discuss the identification and categorization of conceptual change and learner properties to be modeled. Thirdly, how to construct the INQPRO learner model that employs Dynamic Bayesian networks (DBN) to compute a temporal probabilistic assessment of learner's properties that vary over time: awareness of current belief, cognitive conflict, conflict resolution, and ability to accommodate to new knowledge. Towards the end of this article, a sample assessment of the proposed DBN is illustrated through a revisit of the INQPRO Scenario interface
- …
