Simona Vasilache

Children's Social Behavior Analysis System Using BLE and Accelerometer.

We present an IoT-based children’s social behavior analysis system aimed at young children and elementary school students. Our system uses BLE-based ID logs to analyze daily social behaviors, such as how a child spent the day with his/her friends. Furthermore, we also use accelerometer logs to detect the period when the user (i.e., a child) was with friends or not, and what kind of activity (e.g., walking or staying in one place) the user was involved in. We conducted a five-day experiment with four families using our system. We also interviewed the families’ parents and compared their responses with the analyzed results to investigate the accuracy of the above detection and usability of our system. The result shows that our system can detect the period when the child was with other friends or alone, as well as the activity (s)he was involved in.

Detecting Multitasking Work and Negative Routines from Computer Logs

Multitasking on digital media has a negative effect on mental health and concentration. At the same time, the negative effects of computer usage are not immediately obvious to most people. We suggest that people can improve their daily experience on the computer if they pay closer attention to their multitasking activities. To this end, we have constructed a system that detects multitasking work and periodic negative multitasking routines from computer logs. We created two indicators: relax rate and multitasking rate. The relax rate is defined on the basis of heart rate variability information and the multitasking rate is derived from how often users switch their computer windows. We analyze whether users’ multitasking is negative or not and whether or not negative multitasking is part of a periodic routine. We logged the computer activities and heart rate data of one participant for six days.

An adaptive model of teaching computer literacy in the context of multicultural instruction

Computer literacy is becoming a mandatory subject in an increasing number of higher education institutions. At the same time, we can observe an internationalization of higher education all over the world. The educators are challenged to teach culturally sensitive and culturally adaptive courses. We propose the development of a model for teaching strategy of computer literacy in the context of multicultural instruction at the university undergraduate level. Our model will be customizable, so that it can be adapted to class size, disparities in previous knowledge, perception and experience with using learning management systems. Using our model and through frequent quantitative and qualitative analysis, class style can be constantly adapted and adjusted.

Bridging the gap between analysis and design using dependency diagrams

Requirements specifications often make use of a number of scenarios that are interrelated and that depend on each other in many ways. However, they are often treated separately, one by one. We propose a new type of diagrams, named dependency diagrams, which are able to illustrate the various kinds of relationships existing between scenarios. We make use of a scenario matrix for each scenario and we describe the transformation process of scenarios into state machines, based on the information in the scenario matrices, and that in the dependency diagrams. The result is a number of state machines that can be used for detailed design models and code can further be generated from them. Using our approach, we can bridge the gap between analysis and design and we can bring the developer one step closer to the implementation.

Classification Method of Rubbing Haptic Information Using Convolutional Neural Network

In previous research, we proposed a method to collect accelerations in daily haptic behaviors using a ZigBee-based microcomputer. However, the method for classifying the collected data was not sufficiently implemented. We therefore propose applying collected data to classify rubbing haptic information. In this paper, we implemented a classification approach for haptic information collected by our method. We used a convolutional neural network (CNN) to classify the information. We performed a classification experiment in which the CNN classified 18 types of information, 93.2% on average. We also performed an experiment to classify rubbed objects in real-time. The CNN was able to classify five types of objects, about 67.7% on average.

BLE-Based Children’s Social Behavior Analysis System for Crime Prevention

We propose an IoT-based children’s behavior analysis system for crime prevention, aimed at infants and elementary school students. The system logs children’s behavior with accelerometers and Bluetooth low energy (BLE). We conducted a preliminary experiment with a test application to examine whether BLE-based ID logs can be used to analyze daily social behaviors, such as how a child spent the day with his or her friends. The results suggest that the history of behavior with a child’s friends was acquired accurately. Furthermore, the system could detect the period when the user (that is, a child) was with friends or not, and what kind of activity (for example, walking or staying in one place) the user was involved in.

Teaching Software Engineering in a Multicultural Environment

Education in multicultural environments poses challenges for both educators and students. Similarly to other subjects, software engineering teaching is faced with difficulties in the need to adapt the teaching style and contents to the various cultural backgrounds of the students. Based on a small-scale study, this paper attempts to highlight perspectives of students belonging to various cultural backgrounds on software engineering, as well as their views on the practicalities of software development.

Using the Office Desk as a Touch Interface

A system that allows a user to easily operate a computer or tablet while working on a desk was devised. In particular, the desk is changed into an input interface that can detect the touch of a hand. A device that acquires the position data of the hand and a software program that operates the computer or tablet using this device were developed. The device, which uses the office desk as a touch interface, was constructed. The device was used in an application for navigating images displayed on a screen, even while doing other work on the desk (e.g., drawing). In future work, the sensors in the device will be improved, and various applications utilizing the device will be developed and experimentally evaluated.