A comprehensive study on mid-level representation and ensemble learning for emotional analysis of video material

Multimedia Tools and Applications - In today’s society where audio-visual content such as professionally edited and user-generated videos is ubiquitous, automatic analysis of this content is...     

Multi-domain collaborative exploration mechanisms for query expansion in an agent-based filtering framework

Novice users often do not have enough domain knowledge to create good queries for searching information on-line. To help alleviate the situation, exploration techniques have been used to increase the diversity of the search results so that not only those explicitly asked will be returned, but also those potentially relevant ones will be returned too. Most existing approaches, such as collaborative filtering, do not allow the level of exploration to be controlled. Consequently, the search results can be very different from what is expected. We propose an exploration strategy that performs intelligent query processing by first searching usable old queries, and then utilising them to adapt the current query, with the hope that the adapted query will be more relevant to the user’s areas of interest. We applied the proposed strategy to the implementation of a personal information assistant (PIA) set up for user evaluation for 3 months. The experimental results showed that the proposed exploration method outperformed collaborative filtering, and mutation and crossover methods by around 25% in terms of the elimination of off-topic results.     

An ontology-based support for product conceptual design

The research presented in this paper is a follow-up of our prior work involving the development of a graphical modeling tool to support designers at the conceptual design stage. To close the loop for supporting designers in generating design concepts flexibly, fast, and easily, an ontology-based approach for knowledge management that works along with the graphical modeling tool is discussed. Ontology and databases for the tool are developed to promote the systematic capture of design knowledge and efficient reuse of the design knowledge selection. In order to locate the proper information and query the data from the databases, the relationship between the ontology and databases, the data analysis process, ontology enrichment, and the ontology-based query engine are built to offer users multiple design results according to users’ requirements. A tire design example is presented to demonstrate the proposed approach. The ontology-based method described in this paper can help retrieve and save the complex relations, support the reasoning, integrate heterogeneous data resources and offer users more accurate, proper and comprehensive data.     

Design of Adaptive Robot Control System Using Recurrent Neural Network

The use of a new Recurrent Neural Network (RNN) for controlling a robot manipulator is presented in this paper. The RNN is a modification of Elman network. In order to solve load uncertainties, a fast-load adaptive identification is also employed in a control system. The weight parameters of the network are updated using the standard Back-Propagation (BP) learning algorithm. The proposed control system is consisted of a NN controller, fast-load adaptation and PID-Robust controller. A general feedforward neural network (FNN) and a Diagonal Recurrent Network (DRN) are utilised for comparison with the proposed RNN. A two-link planar robot manipulator is used to evaluate and compare performance of the proposed NN and the control scheme. The convergence and accuracy of the proposed control scheme is proved.     

Salt and pepper noise filtering with fuzzy-cellular automata

A new image denoising algorithm is proposed to restore digital images corrupted by impulse noise. It is based on two dimensional cellular automata (CA) with the help of fuzzy logic theory. The algorithm describes a local fuzzy transition rule which gives a membership value to the corrupted pixel neighborhood and assigns next state value as a central pixel value. The proposed method removes the noise effectively even at noise level as high as 90%. Extensive simulations show that the proposed algorithm provides better performance than many of the existing filters in terms of noise suppression and detail preservation. Also, qualitative and quantitative measures of the image produce better results on different images compared with the other algorithms.     

Pre-service teachers' perspectives of the diffusion of information and communications technologies (ICTs) and the effect of case-based discussions (CBDs)

This study investigates pre-service teachers' perspectives of the diffusion of information and communication technologies (ICTs) in elementary education and the effect of case-based discussions (CBDs). The sample consisted of 170 first-year pre-service teachers from elementary teacher education programs of the largest teacher education college in Turkey. The cases used in the study were obtained from a case repository at http://ornekolay.org, indexing teaching cases from elementary classrooms of the capital city of Turkey. The cases were mainly text-based and presented stories of elementary teachers' in-class usage of ICTs. A quasi-experimental pretest-posttest design was executed to test the effect of pre-service teachers' perspectives on ICTs diffusion in elementary teaching. Three scales were developed based on Rogers' Diffusion of Innovation Theory (2003) to measure pre-service teachers' preferred innovativeness, innovation perceptions, and innovation decisions in the use of ICTs. The results showed that pre-service teachers had pre-established perspectives, mainly positive, about the diffusion of ICTs in elementary teaching; their perceptions about innovativeness and relative advantage were the main indicators of persuasion and decision; and CBDs positively affected their perceptions such that their computer-related persuasion and decisions positively increased.     

New classification techniques for electroencephalogram (EEG) signals and a real-time EEG control of a robot

This paper studies the state-of-the-art classification techniques for electroencephalogram (EEG) signals. Fuzzy Functions Support Vector Classifier, Improved Fuzzy Functions Support Vector Classifier and a novel technique that has been designed by utilizing Particle Swarm Optimization and Radial Basis Function Networks (PSO-RBFN) have been studied. The classification performances of the techniques are compared on standard EEG datasets that are publicly available and used by brain–computer interface (BCI) researchers. In addition to the standard EEG datasets, the proposed classifier is also tested on non-EEG datasets for thorough comparison. Within the scope of this study, several data clustering algorithms such as Fuzzy C-means, K-means and PSO clustering algorithms are studied and their clustering performances on the same datasets are compared. The results show that PSO-RBFN might reach the classification performance of state-of-the art classifiers and might be a better alternative technique in the classification of EEG signals for real-time application. This has been demonstrated by implementing the proposed classifier in a real-time BCI application for a mobile robot control.