The impact of students’ behaviour, their approach, emotions and problem difficulty level on the performance prediction, evaluation and overall learning process during online coding activities

Learning process while solving coding problems is quite complex to understand. It is extremely important to understand the skills which are required and gained during learning to code. As a first step to understand the students’ behaviour and approach during learning coding, two online coding assignments or competitions are conducted with a 1-hour time limit. A survey has been conducted at the end of each coding test and answers to different questions have been collected. In depth statistical analysis is done to understand the learning process while solving the coding problems. It involves lots of parameters including students’ behaviour, their approach and difficulty level of coding problems. The inclusion of mood and emotions related questions can improve overall prediction performance but difficulty level matters in the submission status prediction. Two coding assignments or competitions are analysed through in-depth research on 229 (first coding competition dataset) and 325 (second coding competition dataset) data points. The primary results are promising and these results give in depth insights about how learning to solve coding problems is affected by students’ behaviour, their approach, emotions and problem difficulty level.

A Fishery Water Quality Monitoring and Prediction Evaluation System for Floating UAV Based on Time Series

In recent years, fishery has developed rapidly. For the vital interests of the majority of fishermen, this paper makes full use of Internet of Things and air–water amphibious UAV technology to provide an integrated system that can meet the requirements of fishery water quality monitoring and prediction evaluation. To monitor target water quality in real time, the water quality monitoring of the system is mainly completed by a six-rotor floating UAV that carries water quality sensors. The GPRS module is then used to realize remote data transmission. The prediction of water quality transmission data is mainly realized by the algorithm of time series comprehensive analysis. The evaluation rules are determined according to the water quality evaluation standards to evaluate the predicted water quality data. Finally, the feasibility of the system is proved through experiments. The results show that the system can effectively evaluate fishery water quality under different weather conditions. The prediction accuracy of the pH, dissolved oxygen content, and ammonia nitrogen content of fishery water quality can reach 99%, 98%, and 99% on sunny days, and reach 92%, 98%, and 91% on rainy days.

EARTHQUAKE PREDICTION EVALUATION BASED ON VLF DATA USING A NOVEL INTERSECTION-UNION METHOD

Electromagnetic phenomena, especially those in the Very Low Frequency/Low Frequency (VLF/LF) bands are promising for short-term earthquake prediction. Seismo-ionospheric perturbations cause a variety of changes in different receiver-transmitter VLF/LF signal paths. Therefore, independent and simultaneous observations at different points thus in different VLF/LF signal propagation paths are necessary to better predict the earthquake. Most of the previous research on VLF data have been based on one path or limited number of paths which examined perturbations in the time domain and less attention has been paid to estimate the location of the earthquake. In the present research, using wavelet analysis, the temporal variations of seismo-ionospheric perturbations and the approximate time of earthquake are predicted. Clear disturbances are observed two weeks before the Kumamoto earthquake happened in Japan in 2016. The novelty of this study is to present an approach called Intersection-Union method to predict earthquake location. Based on the geometry of a VLF/LF network, the Intersection-Union method was introduced to estimate the earthquake epicenter. This method is based on the overlay of earthquake occurrence probable areas. With simultaneous use of different propagation paths by the Intersection-Union method, an area with a radius of about 300 km was determined as the probable location of the earthquake epicenter. The accuracy of the proposed method is 300 km compared with 1000 km accuracy of other earthquake location prediction scenarios.

An assessment of the thermal impact on the valve torque on cryogenically sub-zero temperatures

A common challenge faced by valve designers for cryogenics is the prediction, evaluation, and conclusion of the most optimum design of the valve hand-wheel due to the enhanced torque required for the valve to operate at sub-zero temperatures. The research efforts are directed towards technical assessment to establish a correlation between the thermal variations and torque values for the valve. The research envisioned an experimental study conducted on Liquid Nitrogen (LIN) Media on an isolation type globe valve of the size of Diameter nominal 15mm on variable pressure value from 1 MPa to 3 MPa with temperature inception from -150 ºC (123 K) to -200 ºC (73 K). The experiment is modeled using the design of experiments methodology subsequently compared with the engineering design analytical methodology to correlate the two methods .

Prediction Model for the Persistence of Sharia Mutual Fund Performance in Indonesian Capital Market

Over the period of 2010 to 2012, the performance of Islamic mutual funds in Indonesia saw a high degree of persistence. However, the persistence rate decreased in the period of 2014 to 2016. Given such fluctuated rate, this research tries to identify the factors that influence the persistence of the mutual fund performance and, based on these factors, creates the predictive modelling of persistence rate. The samples of the study included all sharia mutual funds offered from 2010 to 2016 in Indonesian capital market. To construct the model, we used the Logit equation, while to evaluate the accuracy of the prediction model, we used the Expectation- Prediction Evaluation with a prediction evaluation for success of 0.5. The results of this study indicate that,of the whole mutual fund, the best model is a model involving the following variables: (1) the time interval since the mutual fund was launched, (2) the rank of the mutual funds, whether it was at the top 5 within 1-2 years after the launch, and (3) the number of newcomer funds during persistence testing. The level of accuracy of this model, when it was used to predict the whole sharia mutual fund persistence, was 64%. When the model was used to predict the persistence of equity performance of mutual fund, its level of accuracy rose to 77.78%. Whereas in the use to predict the persistence of fixed income mutual funds the accuracy rate amounted to 70%. The persistence of predictive model for mixed funds was based on different factors of compositions: (1) the number of funds under management, (2) the fact whether the mutual funds are in the top 5 within 1-2 years after the launch, and (3) the number of newly coming funds during persistence testing. This model had an accuracy level of 75%. It is expected that this study be used as a guide for investors wishing to invest in sharia mutual funds.

W-Index: An Index for Evaluating Link Prediction considering Only the Role of Wins

With the emergence of numerous link prediction methods, how to accurately evaluate them and select the appropriate one has become a key problem that cannot be ignored. Since AUC was first used for link prediction evaluation in 2008, it is arguably the most preferred metric because it well balances the role of wins (the testing link has a higher score than the unobserved link) and the role of draws (they have the same score). However, in many cases, AUC does not show enough discrimination when evaluating link prediction methods, especially those based on local similarity. Hence, we propose a new metric, called W-index, which considers only the effect of wins rather than draws. Our extensive experiments on various networks show that the W-index makes the accuracy scores of link prediction methods more distinguishable, and it can not only widen the local gap of these methods but also enlarge their global distance. We further show the reliability of the W-index by ranking change analysis and correlation analysis. In particular, some community-based approaches, which have been deemed effective, do not show any advantages after our reevaluation. Our results suggest that the W-index is a promising metric for link prediction evaluation, capable of offering convincing discrimination.

Use of Wearable Sensors and Machine Learning Methods in Promoting Total Joint Replacement Treatment Outcomes: A Survey

Total Joint Replacement (TJR) surgeries are one of the most prevalent operations that are undergone by the elderly population. With the world population aging, the number of surgeries will continue to increase. A small portion of these surgeries result in complications that require readmissions. These readmissions amount to a significant financial and time burden for both the patients and the hospitals. In the past decade machine learning and wearable sensors have both been used extensively in the healthcare domain but the contribution to the prediction/evaluation and management of TJR is limited. What’s more, to our best knowledge there has been no effort in summarizing the findings from these studies. Therefore, this study highlights what has been achieved by using machine learning and wearable sensors in the TJR context and point out possible research avenues.