Search for: All records

The dual mechanisms of control framework describes two modes of goal-directed behavior: proactive control (goal maintenance) and reactive control (goal activation on task demands). Although these mechanisms are relevant to learner behaviors during interaction with intelligent tutoring systems (ITS), their relation to ITSs is under-researched. We propose a manipulation to induce proactive or reactive control during interaction with an online tutoring system. We present two experiments where students solved problems using either proactive or reactive control. Study 1 validates the manipulation by investigating behavioral measures that reflect usage of the intended strategy and assesses whether either mode impacted learning. Study 2 investigates if alternating between control modes during problem solving affects student performance. 

Underwater wireless communication and network- ing are becoming key enablers of a number of critical marine and underwater applications. Experimentation is underway, in controlled environments as well as at sea, that concerns the deployment of several underwater devices providing wireless communication capabilities to sensors of different nature. Con- trolling the deployment at sea of these devices, remotely and efficiently, is paramount for enabling expedite testing of hardware and protocol development. To address this need, this paper presents the design, development, and testing of a Smart Buoy for real-time remote access to underwater devices and for provision of power and extended computational capabilities. Experimental results are shown concerning the time needed to connect with the Smart Buoy, the power consumption of its operations, and the energy harvesting intake (via solar panels) in time. We also investigate the buoy lifetime when powered by solar panels and supporting acoustic modems over varying traffic scenarios. 

Cognitive control and rule learning are two important mechanisms that explain how goals influence behavior and how knowledge is acquired. These mechanisms are studied heavily in cognitive science literature within highly controlled tasks to understand human cognition. Although they are closely linked to the student behaviors that are often studied within intelligent tutoring systems (ITS), their direct effects on learning have not been explored. Understanding these underlying cognitive mechanisms of beneficial and harmful student behaviors can provide deeper insight into detecting such behaviors and improve predictive models of student learning. In this paper, we present a thinkaloud study where we asked students to narrate their thought processes while solving probability problems in ASSISTments. Students are randomly assigned to one of two conditions that are designed to induce the two modes of cognitive control based on the Dual Mechanisms of Control framework. We also observe how the students go through the phases of rule learning as defined in a rule learning paradigm. We discuss the effects of these different mechanisms on learning, and how the information they provide can be used in student modeling. 

Response time has been used as an important predictor of student performance in various models. Much of this work is based on the hypothesis that if students respond to a problem step too quickly or too slowly, they are most likely to be unsuccessful in that step. However, something that is less explored is that students may cycle through different states within a single response time and the time spent in those states may have separate effects on students’ performance. The core hypothesis of this work is that identifying the different states and estimating how much time is devoted to them in a single response time period will help us predict student performance more accurately. In this work, we de-compose response time into meaningful subcategories that can be indicative of helpful or harmful cognitive states. We then show how a model that is using these subcategories as predictors instead of response time as a whole outperforms both a linear and a non-linear baseline model. 

Underwater networks of wireless sensors deployed along the coast or in the deep water are the most promising solution for the development of underwater monitoring, exploration and surveillance applications. A key feature of underwater networks that can significantly enhance current monitoring applications is the ability to accommodate real-time video information on an underwater communication link. In fact, while today monitoring relies on the exchange of simple discrete information, e.g., water temperature, and particle concentration, among others, by introducing real-time streaming capability of non-static images between wireless underwater nodes one can completely revolutionize the whole underwater monitoring scenario. To achieve this goal, underwater links are required to support a sufficiently high data rate, compatible with the streaming rates of the transmitted video sequence. Unfortunately, the intrinsic characteristic of the underwater propagation medium has made this objective extremely challenging. In this paper, we present the first physical layer transmission scheme for short-range and high-data rate ultrasonic underwater communications. The proposed solution, which we will refer to as Underwater UltraSonar (U2S), is based on the idea of transmitting short information-bearing carrierless ultrasonic signals, e.g., pulses, following a pseudo-random adaptive time-hopping pattern with a superimposed rate-adaptive Reed-Solomon forward error correction (FEC) channel coding. We also present the design of the first prototype of a software-defined underwater ultrasonic transceiver that implements U2S PHY transmission scheme through which we evaluate the U2S performance in real-scenario underwater experiments at the PHY layer, i.e., Bit Error Rate (BER) extensively, and at the application layer, i.e., structural similarity (SSIM) index. Results show that U2S links can support point-to-point data rate up to 1.38 Mbps and that by leveraging the flexibility of the adaptive time-hopping and adaptive channel coding techniques, one can trade between link throughput and energy consumption, still satisfying application layer requirements.