Maria Goga

Bio: Maria Goga is an academic researcher. The author has contributed to research in topics: Berendsen thermostat & Message Passing Interface. The author has an hindex of 3, co-authored 6 publications receiving 53 citations.

Method for measuring the heart rate through fingertip using a low-end video camera and its application in self care

Abstract: This article presents a method for monitoring the heart rate using a low-end video camera. The user places the fingertip on the camera lens and the software detects the periodic variations in light intensity caused by the pulsation of blood in the capillary tissue. The measurement technique is based on extracting beat-to-beat intervals by passing the color intensity average through a processing pipeline comprised of six stages. Our tests indicate a measurement error below 3 bpm, when compared to commonly available home care devices. We present a possible application of our method in the area of stress diagnosis and treatment. The application can be used at home to monitor personal health and enable individuals to perform enhanced self care.

StressFree--A Tool for Stress Determination and Treatment through Computer Music Generation

Abstract: This paper describes a framework for determining stress by measuring the heart rate and treating it through computer music generation. We present a practical and computationally inexpensive technique for measuring the heart rate using the low-end video cameras already present in a wide range of consumer electronics. Our method for treating stress is based on music therapy using computer generated music. Currently the heart rate monitor application and the computer music generation tool are implemented. Further work includes the analysis of heart rate variability and the integration of the framework on a smart phone.

Extracting Knowledge from the Bible: A Comparison between the Old and the New Testament

Abstract: The objective of this work is to present a comparison between the Old Testament and the New Testament in terms of knowledge extraction and ontology learning. It is a knows fact that these two books have many differences in term of size, practice of worship, prophecy and there is also a difference in the time period when they were written. By applying the ontology learning and knowledge extraction methods we were interested do see if these differences are revealed and what are the similarities among them. Ontology learning can be applied for the semantic analysis of text, in order to extract concepts, relations, which can be further used for automated summaries or critical comparison. Such activities are important in education as they can allow dynamic creation of content or analyses that can be further used in the educational process. Since ontology-learning methods require large corpus of unstructured data, we have chosen the Bible as source for the text. In this way, the new developed methods are validated, and they can be used successfully in other educational domains. The Bible is the religious text of Christians and Jews. The Bible contains a collection of scriptures that was written by many authors, at different time and locations. Computationally, the Bible contains semi-structured information due to its organized structure of scriptures and numbered chapters. We have used Text2Onto as the main tool in order to obtain the most relevant concepts from the New Testament and then from The Old Testament. After that we analyze the most relevant concepts and the range of similarity for each domain identified in the New Testament and in The Old Testament. We can mention that there are no studies reported in the literature using ontology extraction for this religious domain. Those methods can be employed for automatic generation of content that can be further used in the educational process.

Benchmarking MD systems simulations on the graphics processing unit and multi-core systems

Abstract: Molecular dynamics facilitates the simulation of a complex system to be analyzed at molecular and atomic levels. Simulations can last a long period of time, even months. Due to this cause the graphics processing units (GPUs) and multi-core systems are used as solutions to overcome this impediment. The current paper describes a comparison done between these two kinds of systems. The first system used implies the graphics processing unit, respectively CUDA with the OpenMM molecular dynamics package and OpenCL that allows the kernels to run on the GPU. This simulation is done on a new thermostat which mixes the Berendsen thermostat with the Langevin dynamics. The second comprises the molecular dynamics simulation and energy minimization package GROMACS which is based on a parallelization through MPI (Message Passing Interface) on multi-core systems. The second simulation uses another new thermostat algorithm related respectively, dissipative particle dynamics — isotropic type (DPD-ISO). Both thermostats are innovative, based on a new theory developed by us. Results show that parallelization on multi-core systems has a performance up to 33 times greater than the one performed on the graphics processing unit. In both cases temperature of the system was maintained close to the one taken as reference. For the simulation using the CUDA GPU, the faster runtime was obtained when the number of processors was equal to four, the simulation speed being 3.67 times faster compared to the case of only one processor.

Usage of Machine Learning for Strategic Decision Making at Higher Educational Institutions

Abstract: Decisions made at the strategic level of Higher Educational Institutions (HEIs) affect policies, strategies, and actions that the institutions make as a whole. Decision’s structures at HEIs are depicted in this paper and their effectiveness in supporting the institutions’ governance. The disengagement of the stakeholders and the lack of using efficient computational algorithms lead to 1) the decision process takes longer; 2) the “whole picture” is not involved along with all data necessary; and 3) small academic impact is produced by the decision, among others. Machine learning is an emerging field of artificial intelligence that using various algorithms analyzes information and provides a richer understanding of the data contained in a specific context. Based on the author’s previous works, we focus on supporting decision-making at a strategic level, being deans’ concerns the preeminent mission to bolster. In this paper, three supervised classification algorithms are deployed to predict graduation rates from real data about undergraduate engineering students in South America. The analysis of receiver operating characteristic (ROC) curve and accuracy are executed as measures of effectiveness to compare and evaluate decision tree, logistic regression, and random forest, where this last one demonstrates the best outcomes.

Literature Survey on Student’s Performance Prediction in Education using Data Mining Techniques

Abstract: One of the most challenging tasks in the education sector in India is to predict student's academic performance due to a huge volume of student data. In the Indian context, we don't have any existing system by which analyzing and monitoring can be done to check the progress and performance of the student mostly in Higher education system. Every institution has their own criteria for analyzing the performance of the students. The reason for this happing is due to the lack of study on existing prediction techniques and hence to find the best prediction methodology for predicting the student academics progress and performance. Another important reason is the lack in investigating the suitable factors which affect the academic performance and achievement of the student in particular course. So to deeply understand the problem, a detail literature survey on predicting student’s performance using data mining techniques is proposed. The main objective of this article is to provide a great knowledge and understanding of different data mining techniques which have been used to predict the student progress and performance and hence how these prediction techniques help to find the most important student attribute for prediction. Actually, we want to improve the performance of the student in academic by using best data mining techniques. At last, it could also provide some benefits for faculties, students, educators and management of the institution.

A Course Recommender System based on Graduating Attributes

Abstract: Assessing learning outcomes for students in higher education institutes is an interesting task with many potential applications for all involved stakeholders (students, administrators, potential employers, etc.). In this paper, we propose a course recommendation system for students based on the assessment of their "graduate attributes" (i.e. attributes that describe the developing values of students). Students rate the improvement in their graduating attributes after a course is finished and a collaborative filtering algorithm is utilized in order to suggest courses that were taken by fellow students and rated in a similar way. An extension to weigh the most recent ratings as more important is included in the algorithm which is shown to have better accuracy than the baseline approach. Experimental results using correlation thresholding and the nearest neighbors approach show that such a recommendation system can be effective when an active neighborhood of 10-15 students is used and show that the numbers of users used can be decreased effectively to one fourth of the whole population for improving the performance of the algorithm.