Reza GhasemAghaei

Ant Colony-Based Reinforcement Learning Algorithm for Routing in Wireless Sensor Networks

The field of routing and sensor networking is an important and challenging research area of network computing today. Advancements in sensor networks enable a wide range of environmental monitoring and object tracking applications. Routing in sensor networks is a difficult problem: as the size of the network increases, routing becomes more complex. Therefore, biologically-inspired intelligent algorithms are used to tackle this problem. Ant routing has shown excellent performance for sensor networks. In this paper, we present a biologically-inspired swarm intelligence-based routing algorithm, which is suitable for sensor networks. Our proposed ant routing algorithm also meet the enhanced sensor network requirements, including energy consumption, success rate, and time delay. The paper concludes with the measurement data we have found.

Ant colony-based many-to-one sensory data routing in Wireless Sensor Networks

An ant colony-based routing protocol is presented in this paper that is specifically designed to route many-to-one sensory data in a multi-hop wireless sensor network (WSN). Because a many-to-one routing paradigm generates lots of traffic in a multi- hop WSN resulting in greater energy wastage, higher end-to-end delay and packet loss, the proposed routing protocol also comes with a lightweight congestion control mechanism, which is capable of handling both event-based and periodic upstream sensory data flow to the base station. The proposed protocol works in two-phases. During the first phase, the protocol uses ant-based intelligence to find and enforce the shortest path and in the second phase, when the actual many- to-one sensory data transmission takes place, the protocol combines the knowledge gained during the first phase with the congestion control mechanism to avoid packet loss and traffic while routing the sensory data. When compared with the related algorithms, the proposed algorithm shows promising results.

M-IAR: Biologically Inspired Routing Protocol for Wireless Multimedia Sensor Networks

In this paper, we propose multimedia-enabled improved adaptive routing (M-IAR) that is optimized for single-source-to- single-destination multimedia sensory data traffic. It is an extension of the improved adaptive routing (IAR) algorithm presented in our earlier work, in response to the increasing number of applications incorporating wireless multimedia sensors such as wireless microphones and cameras. M-IAR is a swarm-intelligent- based algorithm exploiting the concept of ant colony optimization to optimize end-to-end delay, jitter, latency, energy consumption, packet survival rate, and routing path, within the multimedia wireless sensor network. The presented algorithm is proven to satisfy its goals through a series of computer simulations.

Empirical study of a vision-based depth-sensitive human-computer interaction system

This paper proposes the results of a user study on vision-based depth-sensitive input system for performing typical desktop tasks through arm gestures. We have developed a vision-based HCI prototype to be used for our comprehensive usability study. Using the Kinect 3D camera and OpenNI software library we implemented our system with high stability and efficiency by decreasing the ambient disturbing factors such as noise or light condition dependency. In our prototype, we designed a capable algorithm using NITE toolkit to recognize arm gestures. Finally, through a comprehensive user experiment we compared our natural arm gestures to the conventional input devices (mouse/keyboard), for simple and complicated tasks, and in two different situations (small and big-screen displays) for precision, efficiency, ease-of-use, pleasantness, fatigue, naturalness, and overall satisfaction to verify the following hypothesis: on a WIMP user interface, the gesture-based input is superior to mouse/keyboard when using big-screen. Our empirical investigation also proves that gestures are more natural and pleasant to be used than mouse/keyboard. However, arm gestures can cause more fatigue than mouse.

Evaluating Software for Affective Education: A Case Study of the Affective Walkthrough

We present and discuss the use of a proposed walkthrough method to evaluate the affective design of an educational multimodal software system. We conducted a case study using the walkthrough. The software we studied was designed to support an educational objective of making the learners more engaged and reflective, and the software’s aim was to use narrative to help the learners tell a visual story. We recruited participants to apply the method, and we observed the evaluation process. Our findings were that the evaluation method was effective, but we observed a number of effects that suggested necessary improvements.

Design practices for multimodal affective mathematical learning

In this paper we focus on interaction design for multimodal software in affective education, and provide a case study of our MADE (Multimodal Affect for Design and Evaluation) framework. We are considering the sensory modalities, affective and cognitive strategies and trying to solve mathematical learning difficulties such as lack of attention, distraction, stress or disabilities. Using a multimodal affective learning system will increase the encouragement in learning, and will help students develop grounded understanding of proportional equivalence e.g. 1/3 = 2/6.

Affective walkthroughs and heuristics: Evaluating minecraft hour of code

This paper presents an evaluation of Code.org’s Minecraft Hour of Code that was created to encourage and support people initial learning of computer programming. In particular, this web-based software uses a spatial model world, where the learner’s programs manipulate the world. We applied the Affective Walkthrough and the Affective Heuristic Evaluation, proposed evaluation methods for affective learning in multimodal educational software. Our findings provided illumination about the Minecraft Hour of Code approach, highlighting some aspects that are successful, and others where improvement appears necessary. We also gained insight about the evaluation methods and their effectiveness.

MADE Ratio: Affective Multimodal Software for Mathematical Concepts

This paper addresses the use of multiple sensory modalities and affective strategies in learning mathematics. A case study is presented where these domains are used to design a mathematical ratio system. We adopted a multimodal approach used by other researchers, and applied our proposed design methods to create the MADE Ratio system. We then recruited participants to test the usability of the system. Our findings were that the design methods were effective, but we also gained insight about how they could be improved.