Showing papers in "Cognitive Systems Research in 2018"

TL;DR: A blockchain-based data sharing system is proposed to tackle the issue of privacy of patients, which employs immutability and autonomy properties of the blockchain to sufficiently resolve challenges associated with access control and handle sensitive data.

TL;DR: A new deep convolutional autoencoder (CAE) model for compressing ECG signals that can learn to use different ECG records automatically and allow secure data transfer in a low-dimensional form to remote medical centers is proposed.

TL;DR: The experimental result reveals that the proposed bio-inspired algorithm finds an optimal subset of features, maximizing the accuracy, minimizing number of features selected and is more stable than the current cuttlefish algorithm.

TL;DR: In this paper, Sobel and Prewitt, algorithms are used for edge detection using 180 nm technology, the algorithms are implemented using VLSI, and digital IC design of the architecture is presented.

TL;DR: This paper proposes a method for implementing ethical behaviour in robots inspired by the simulation theory of cognition and implements a version of this architecture on a humanoid NAO robot so that it behaves according to Asimov’s laws of robotics.

TL;DR: A computer aided depression diagnosis system using newly designed bandwidth-duration localized (BDL) three-channel orthogonal wavelet filter bank and EEG signal for the detection of depression and attained the perfect value of 1 for area under the curve (AUC) of receiver’s operating characteristics (ROC) using seven features.

TL;DR: A CNN-based framework is built to automatically classify the blood cell images into subtypes of the cells, and the results show that the proposed model provide better results in terms of evaluation parameters.

TL;DR: The term "Cognitive Architectures" indicates both abstract models of cognition, in natural and artificial agents, and the software instantiations of such models which are then employed in the field of cognition.

TL;DR: An analysis of two problematic aspects affecting the representational level of cognitive architectures, namely: the limited size and the homogeneous typology of the encoded and processed knowledge are identified and characterized.

TL;DR: This work demonstrates the use of IR cameras in the field of AAL and discusses its performance in human action recognition (HAR).

TL;DR: The manuscript attempts to unveil the hidden capabilities of deep neural networks in enabling machines perform the human way tasks which can be learned through what the authors call observation and experience.

TL;DR: The objective of this manuscript is to present some new operational laws called as logarithm operational laws with real number base λ for the single-valued neutrosophic (SVN) numbers and to present a multiattribute decision making method to solve the decision-making problems.

TL;DR: Two stable multistep backward cloud conversion algorithms are proposed, which lays the foundation for the realization of a stable bidirectional cognitive calculation process and shows that the proposed method has lower mean error and is obviously better than other algorithms, which fully proves the effectiveness of the method.

TL;DR: The experimental results showed that the probabilistic neural network (PNN) had the minimum error rate and second types of errors, while the PNN model had the highest AUC value and was robust.

TL;DR: An improved deep convolutional neural network is proposed, which takes advantage of the Inception V2 with batch normalization (BN) instead of convolutionAL neural layers in the faster region convolved neural network (Faster RCNN) offering multiscale image features to the region proposal network (RPN).

TL;DR: This research developed the reengineering design of the management concepts, organization structure and management of the U-I-R collaborative innovation relying on modern management thought and information technology, to realize improvements and innovations in knowledge acquisition, knowledge sharing, knowledge integration and knowledge application.

TL;DR: Network of “conscious agents” as defined by Hoffman and Prakash (2014) are shown to provide a robust and intuitive representation of perceptual and cognitive processes in the context of the Interface Theory of Perception.

TL;DR: A novel approach to adding primitive evaluative capabilities to a cognitive architecture by developing two models that demonstrate the impact of affective valence and arousal on memory and decision-making.

TL;DR: This paper mainly studies the new expression and operations of single value neutrosophic uncertain linguistic variables and its application in multiple attribute group decision-making (MAGDM).

TL;DR: The evolution of one such framework, I carus, is reviewed, discussing the representational and processing assumptions made by different versions of the architecture, their relation to alternative theories, and some promising directions for future research.

TL;DR: This work proposes a new minimum spanning tree (MST) feature extraction approach on the basis of the phase coherence (PC) and a power spectrum density (PSD) method, and develops an automated fatigue detection system integrated between the novel fusion feature (FBN-PSD-FF) and extreme learning machine (ELM).

TL;DR: It is hypothesized that with enough training and experience, teams should become increasingly stable, ultimately reaching an optimal blend of stability and flexibility and as autonomous agents become increasingly flexible and adaptive, HATs should trend toward this moderate level of stability.

TL;DR: The optimization of intelligently optimized long-distance multimedia sports teaching system has certain operability and can be used to optimize school sports curriculum.

TL;DR: A special synergy between social hierarchy and communal ritual is found: only their combination improved the extent of social coordination, whereas the introduction of centralization and top-down influence by themselves had no effect.

TL;DR: A hybrid algorithm integrating kernel principal component analysis (KPCA) and the conventional RoF algorithm is proposed to overcome the classification difficulty for linearly inseparable datasets and provides higher classification accuracy rates compared with other ensemble machine learning methods.

TL;DR: An advanced encryption scheme is proposed to increase the effective security level while accessing the primary spectrum under eavesdropper scenario and the proposed methodology results in the secrecy rate maximization and the power consumption is minimized.

TL;DR: A prototype to simulate decision scenarios was developed and it was found that agents are capable of acting according to the decision-makers’ intentions and fundamentally benefit from different possible behavioral styles, just as a face-to-face meeting benefits from the heterogeneity of its participants.

TL;DR: The principle of dynamical similitude is demonstrated from the use of the same multifractal method that was used to extract team-level experience from the neurophysiological data of individual team members to the analysis of a large scale economic phenomenon, the stock market index.

TL;DR: AHP (Analytic Hierarchy Process) model based upon four significant attributes of the word co-occurrence networks have been proposed to rank the keyphrases and most frequently occurring segment is identified as an influential segment.

TL;DR: Analysis of panel data of 80 SMEs of advanced manufacture collected during the period from 2013 to 2015 shows that the inverted-U relationship still exists in the influences brought by intellectual property protection to enterprise values.