NUP Academic Publications - Ακαδημαϊκές Δημοσιεύσεις ΠΝΠ
http://hdl.handle.net/11728/1
Here you can find all the Academic Publications of the Faculty of the Neapolis University in Cyprus - Εδώ μπορείτε να βρείτε όλες της Ακαδημαϊκές Δημοσιεύσεις του προσωπικού του Πανεπιστημίου Νεάπολις Πάφου2021-03-06T05:51:02ZA distributed, plug-n-play algorithm formulti-robot applications with a priorinon-computable objective functions
http://hdl.handle.net/11728/11739
A distributed, plug-n-play algorithm formulti-robot applications with a priorinon-computable objective functions
Kapoutsis, Athanasios Ch.; Chatzichristofis, Savvas A.; Kosmatopoulos, Elias B.
This paper presents a distributed algorithm applicable to a wide range of practical multi-robot applications. In such multi-robot applications, the user-defined objectives of the mission can be cast as a general optimization problem, withoutexplicit guidelines of the subtasks per different robot. Owing to the unknown environment, unknown robot dynamics,sensor nonlinearities, etc., the analytic form of the optimization cost function is not available a priori. Therefore, standardgradient-descent-like algorithms are not applicable to these problems. To tackle this, we introduce a new algorithm thatcarefully designs each robot’s subcost function, the optimization of which can accomplish the overall team objective.Upon this transformation, we propose a distributed methodology based on the cognitive-based adaptive optimization(CAO) algorithm, that is able to approximate the evolution of each robot’s cost function and to adequately optimize itsdecision variables (robot actions). The latter can be achieved by online learning only the problem-specific characteristicsthat affect the accomplishment of mission objectives. The overall, low-complexity algorithm can straightforwardlyincorporate any kind of operational constraint, is fault tolerant, and can appropriately tackle time-varying cost functions.A cornerstone of this approach is that it shares the same convergence characteristics as those of block coordinatedescent algorithms. The proposed algorithm is evaluated in three heterogeneous simulation set-ups under multiplescenarios, against both general-purpose and problem-specific algorithms.
2019-05-01T00:00:00ZStudying Affective Tutoring Systems for Mathematical Concepts
http://hdl.handle.net/11728/11738
Studying Affective Tutoring Systems for Mathematical Concepts
Mastrodimos, Dimitrios; Chatzichristofis, Savvas A.
Students face difficulties in learning mathematical processes. As a result, they have
negative emotions toward mathematics. The use of technology is employed to
change the student’s attitude toward mathematics. Some methods utilize intelligent
tutoring systems to recognize student’s emotional state and adapt the learning process
accordingly. These systems, known as affective tutoring systems (ATSs), sense
the emotional state of a student and then intelligently attempt to suggest appropriate
strategies that can guide the learning process and ultimately shift the negative attitude
of students toward mathematical learning. This article presents a survey of
ATSs, which teach mathematic content, and tries to find common elements among
them. It examines the kind and the number of student’s emotions that can be recognized
and the strategies and methods that these ATSs use to recognize student’s
emotional state. There are findings that agree with other studies about the recognized
emotions and the methods that are used.
2019-07-02T00:00:00ZRandomblocks: A transparent, verifiable blockchain-based system for random numbers
http://hdl.handle.net/11728/11737
Randomblocks: A transparent, verifiable blockchain-based system for random numbers
Christodoulou, Klitos; Chatzichristofis, Savvas A.; Sirakoulis, Georgios Ch.; Christodoulou, Panayiotis
Games-of-chance require high-levels of trust between participants that is often uncertain and difficult to enforce. The unique characteristics introduced by the blockchain technology can be leveraged to inform a verifiable but transparent pseudo-random generation process that at the same time eliminates the need of an external trustee service or oracle to guarantee the fair execution of the process. We propose a process that builds on a one-dimensional Cellular Automaton (CA) where the evolution of the CA aligns to the evolution of a blockchain. Given an initial seed defined as the point in time where the evolution of the CA is triggered, the set of transition rules, along with the finite number of evolution steps, any external oracle is able to verify and backtrack (but not predict) the outcome of the process. The effectiveness of the implemented system is confirmed by the use of various statistical testing suites that confirm the existence of a set of statistical properties required to produce sufficient pseudo-random number sequences.
2019-01-01T00:00:00ZSocial Robots in Special Education: Creating Dynamic Interactions for Optimal Experience
http://hdl.handle.net/11728/11736
Social Robots in Special Education: Creating Dynamic Interactions for Optimal Experience
Amanatiadis, A.; Kaburlasos, Vasileios G.; Dardani, Christina; Chatzichristofis, Savvas A.; Mitropoulos, Athanasios
Recent research has proved the positive therapeutic impacts of robot interaction with children diagnosed with the autism spectrum condition. Until now, most of the evaluated treatment methods apply one-to-one sessions between a single robot and a child. This article explores the potential therapeutic effects of multirobot-assisted therapies, along with a proposed game playlist for pursuing such interactive sessions. Considerations for the therapeutic objectives, such as the improvement in social communication and interaction skills, joint attention, response inhibition, and cognitive flexibility are also explored. Finally, general procedures and guidelines are provided to further assist the adoption and use of such multirobot sessions.
2020-04-02T00:00:00Z