Chapter 5. Meta-learning approach to regularization – case study: blood glucose prediction

Electronic learning or online learning is a part of recent education which is dramatically used in universities all over the world. As well as the use and integration of e-learning is at the crucial stage in all developing countries. It is the most significant part of education that enhances and improves the educational system. This paper is to examine the hindrances that influence e-learning in Nigerian university system. In order to have an inclusive research, a case study research was performed in Evangel University, Akaeze, southeast of Nigeria. The paper demonstrates similar hindrances on country side. This research is a blend of questionnaires and interviews, the questionnaires was distributed to lecturers and an interview was conducted with management and information technology unit. Research had shown the use of e-learning in university education which has influenced effectively and efficiently the education system and that the University education in Nigeria is at the crucial stage of e-learning. Hence, some of the hindrances are avoiding unbeaten integration of e-learning. The aim of this research is to unravel the barriers that impede the integration of e-learning in universities in Nigeria. Nevertheless, e-learning has modified the teaching and learning approach but integration is faced with many challenges in Nigerian University.

Download Full-text

Examining Sensor Agreement in Neural Network Blood Glucose Prediction

Journal of Diabetes Science and Technology ◽

10.1177/19322968211018246 ◽

2021 ◽

pp. 193229682110182

Author(s):

Aaron P. Tucker ◽

Arthur G. Erdman ◽

Pamela J. Schreiner ◽

Sisi Ma ◽

Lisa S. Chow

Keyword(s):

Neural Network ◽

Blood Glucose ◽

Patient Specific ◽

Sensor Location ◽

Effective Care ◽

Freestyle Libre ◽

Patients With Diabetes ◽

Interstitial Glucose ◽

Continuous Glucose Monitors ◽

Glucose Prediction

Successful measurements of interstitial glucose are a key component in providing effective care for patients with diabetes. Recently, there has been significant interest in using neural networks to forecast future glucose values from interstitial measurements collected by continuous glucose monitors (CGMs). While prediction accuracy continues to improve, in this work we investigated the effect of physiological sensor location on neural network blood glucose forecasting. We used clinical data from patients with Type 2 Diabetes who wore blinded FreeStyle Libre Pro CGMs (Abbott) on both their right and left arms continuously for 12 weeks. We trained patient-specific prediction algorithms to test the effect of sensor location on neural network forecasting ( N = 13, Female = 6, Male = 7). In 10 of our 13 patients, we found at least one significant ( P < .05) increase in forecasting error in algorithms which were tested with data taken from a different location than data which was used for training. These reported results were independent from other noticeable physiological differences between subjects (eg, height, age, weight, blood pressure) and independent from overall variance in the data. From these results we observe that CGM location can play a consequential role in neural network glucose prediction.

Download Full-text

Satisfaction and Consumption Emotions of Library Users at a Public University in Mexico: A Case Study

Libri ◽

10.1515/libri-2020-0002 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Blanca-Lidia Miranda-Valencia

Keyword(s):

Education Institution ◽

Public University ◽

Library Services ◽

Learning Approach ◽

Business Research ◽

Consumption Emotions ◽

Library Users ◽

Machine Learning Approach ◽

The Relationship

Abstract Consumption emotions are not always considered when satisfaction with library services is assessed. In this research, consumption emotions perceived by users of eight different libraries of a Mexican higher education institution are identified when using library services. Laros and Steenkamp. 2005. “Emotions in Consumer Behavior: A Hierarchical Approach.” Journal of Business Research 58: 1437–45. https://doi.org/10.1016/j.jbusres.2003.09.013 hierarchical scale was used to assess library users’ consumption emotions. The relationship between those emotions and the users’ satisfaction is then established and analyzed using both descriptive statistics analysis and an entropy-oriented machine learning approach. The first approach suggests that users feel more positive consumption emotions (contentment and happiness) than negative emotions (anger). The entropy analysis shows that the identified consumption emotions have a great prediction power over the satisfaction level that users will manifest. This research contributes to the issue of satisfaction assessment by including library users’ consumption emotions in Mexico.

Download Full-text