Modulation Scheme for Biasing the Emotional Process of Autonomous Agents

Autonomous agents (AAs) are capable of evaluating their environment from an emotional perspective by implementing computational models of emotions (CMEs) in their architecture. A major challenge for CMEs is to integrate the cognitive information projected from the components included in the AA's architecture. In this chapter, a scheme for modulating emotional stimuli using appraisal dimensions is proposed. In particular, the proposed scheme models the influence of cognition on appraisal dimensions by modifying the limits of fuzzy membership functions associated with each dimension. The computational scheme is designed to facilitate, through input and output interfaces, the development of CMEs capable of interacting with cognitive components implemented in a given cognitive architecture of AAs. A proof of concept based on real-world data to provide empirical evidence that indicates that the proposed mechanism can properly modulate the emotional process is carried out.

The Layout of Sentiment Lexica in Word Vector Space

Sentiment lexicons play an important role in opinion mining systems and cognitive linguistics. Previous work aimed mostly at creating sentiment lexicons, but not thorough research into their fundamental properties. In this chapter, the arrangement of sentiment lexica in the multidimensional space of distributed word representations is studied. A hypothesis on the existence of sentiment lexica concentration areas is introduced, and it is tested on the basis of the joint analysis of the distribution of sentiment words and general lexica. The results of the test allow to confirm the proposed hypothesis for universal and domain-oriented sentiment lexicons. Also, the experiments discover the words which more than 80% of the sentiment lexica is concentrated around.

Inter-Hemispherical Investigations on the Functional Connectivity in Controls and Autism Spectrum Using Resting State fMRI

Autism spectrum disorders are connected with disturbances of neural connectivity. Functional connectivity is typically examined during a cognitive task, but also exists in the absence of a task. While a number of studies have performed functional connectivity analysis to differentiate controls and autism individuals, this work focuses on analyzing the brain activation patterns not only between controls and autistic subjects, but also analyses the brain behaviour present within autism spectrum. This can bring out more intuitive ways to understand that autism individuals differ individually. This has been performed between autism group relative to the control group using inter-hemispherical analysis. Indications of under connectivity were exhibited by the Granger Causality (GC) and Conditional Granger Causality (CGC) in autistic group. Results show that as connectivity decreases, the GC and CGC values also get decreased. Further, to demark the differences present within the spectrum of autistic individuals, GC and CGC values have been calculated.

Eye Movements and Mirror Neurons

Denotational mathematics, in the context of universal algebra, may provide algebraic structures that are able to formalize human eye movement dynamics with respect to Husserlian phenomenological theory, from which it is then possible to make briefly reference to some further relations with mirror neuron system and related topics. In this way, the authors have provided a first instance of fruitful application of socio-humanities (to be precise, philosophy and sociology) in exact/natural science used in formalizing processes.

Trends and Technologies in Big Data Processing

Data type and amount in human society is growing at an amazing speed, which is caused by emerging new services such as cloud computing, internet of things, and location-based services. The era of big data has arrived. As data has been a fundamental resource, how to manage and utilize big data better has attracted much attention. Especially with the development of the internet of things, how to process a large amount of real-time data has become a great challenge in research and applications. Recently, cloud computing technology has attracted much attention to high performance, but how to use cloud computing technology for large-scale real-time data processing has not been studied. In this chapter, various big data processing techniques are discussed.

Ocean Navigation Method Based on Multi-System and Multi-Source Data Fusion

Ship navigation requires accurate positioning, navigation and timing (PNT) data. PNT data from a single source has uncertainties and potential risks. Wrong PNT data has a huge impact on ship maneuvering, and at the same time, it may cause huge losses to national assets and national security. This chapter proposes a data fusion algorithm based on single-frequency global navigation satellite system (GNSS) and inertial navigation system (INS) to obtain PNT data, which can improve the availability, accuracy, reliability, continuity, and robustness. The experimental results show that the data fusion method combining median filtering and Kalman filtering can improve the system's ability to acquire PNT data. When blocking GNSS acquisition of PNT data, relying on INS, you can still obtain PNT data, which can make up for the ability to obtain PNT data from GNSS.

Quality Estimation for Facial Biometrics

Over past decade, behavioral biometric systems based on face recognition became leading commercial systems that meet the need for fast and efficient confirmation of a person's identity. Facial recognition works on biometric samples, like image or video frames, to recognize people. The performance of an automated face recognition system has a strong relationship with the quality of the biometric samples. In this chapter, the authors propose a quality estimation method based on a linear regression analysis to characterize the relationship between different quality factors and the performance of a face recognition system. The regression model can predict the overall quality of a facial sample which reflects the effects of various quality factors on that sample. The authors evaluated the quality estimation model on the Extended Yale Database B, finally formulating a data set of samples which will enable efficient implementation of biometric facial recognition.

Visualization of Event-Related Changes in Brain Networks During Attention-Demanding Tasks

Attention is the primary cognitive process to induce a response to a stimulus, and maintaining the attentive state continuously for a prolonged period of time is known as sustained attention, which is vital for performing any task. This study aims at visualizing the event-related changes in brain networks during attention demanding task with the help of electroencephalography (EEG) recordings. The results showed significant increase (p<0.05) in relative theta and gamma power during task compared to rest time, whereas in alpha band the relative power was significantly higher (p<0.05) during rest when compared to task. The event-related synchronization (ERS) and event-related desynchronization (ERD) in relative theta power and relative alpha power respectively was observed particularly in the parietal cognitive processing electrodes. The study concludes that theta synchronization and alpha desynchronization noted at parietal cortex that is associated with attention resulted in improving the task performance with minimal errors.

Ensemble Learning via Extreme Learning Machines for Imbalanced Data

Ensembles are known to reduce the risk of selecting the wrong model by aggregating all candidate models. Ensembles are known to be more accurate than single models. Accuracy has been identified as an important factor in explaining the success of ensembles. Several techniques have been proposed to improve ensemble accuracy. But, until now, no perfect one has been proposed. The focus of this research is on how to create accurate ensemble learning machine (ELM) in the context of classification to deal with supervised data, noisy data, imbalanced data, and semi-supervised data. To deal with mentioned issues, the authors propose a heterogeneous ELM ensemble. The proposed heterogeneous ensemble of ELMs (AELME) for classification has different ELM algorithms, including regularized ELM (RELM) and kernel ELM (KELM). The authors propose new diverse AdaBoost ensemble-based ELM (AELME) for binary and multiclass data classification to deal with the imbalanced data issue.

Oil and Gas Production Prediction Based on SVM and Improved Particle Swarm Optimization

Cognitive information is widely used in the field of oil and gas, where production forecasts are of great importance to companies. In this chapter, combining support vector machine and improved particle swarm optimization algorithm, a gas field production prediction model is established, and the model is validated by the actual production data of an enterprise over the years. The results show that the model has good convergence, high prediction accuracy, and training speed and can predict its output more accurately. The method adopted in this chapter is the development of cognitive information technology. The authors have reason to believe that with the continuous development of cognitive information technology, it will have a far-reaching impact on social progress.