Alzheimer's Disease (AD) frequently manifests in visuomotor impairments, disrupting cholinergic signaling from the brainstem to the Thalamic Reticular Nucleus (TRN). The contribution of this work lies in the development of a biologically informed computational framework to model astrocyte mediated restoration of synaptic transmission, measured by a 'release probability (PR)' in TRN under cholinergic depletion. The model simulates three physiological states-healthy, damaged, and recovered by incorporating dual astrocytic mechanisms i.e., depolarization induced suppression excitation (DSE) and endocannabinoid mediated synaptic potentiation (e-SP). This is validated through in-vivo experiments conducted using functional near-infrared spectroscopy (fNIRS) in mice, performing visuomotor integration tasks. Both computational simulations and experimental measurements demonstrate that astrocytic feedback from functional thalamocortical relay cells (TCR) and interneurons (IN) can restore PR partially to approximately 70% of healthy levels despite complete ACh depletion. The bounded, asymmetric temporal dynamics, consistent with beta distribution characteristics reflect biologically realistic regulatory mechanisms maintaining synaptic homeostasis, exhibiting rapid initial potentiation followed by gradual decay. Sensitivity analyses reveal that when modulated with identical parameter values, excitatory TCR terminals produce greater PR with increasing astrocytic strengthening rate of indirect signaling, while inhibitory IN terminals dominate PR recovery under elevated astrocyte synapse coupling weights of indirect signaling. This highlights how excitatory and inhibitory astrocyte-targeted pathways work in tandem to shape recovery in a coordinated manner. The quantitative agreement between computational predictions and experimental measurements (within 2% error) provides evidence supporting astrocyte-based neuromodulation as a biologically grounded mechanism for restoring visuomotor function in AD.

The paper introduces an innovative approach to evaluate the creative potential of individuals based on their analogical reasoning abilities, utilizing an Electroencephalography based data acquisition system. The brain signals recorded during analogical problem-solving tasks undergo pre-processing and transformation into brain connectivity networks using the Pearson's correlation coefficient technique. Through centrality-based feature analysis, the brain's hub lobes involved in the cognitive task are identified, showcasing the active participation of the bilateral orbito-frontal cortex and the right supra-marginal gyrus for successful problem solvers. The extracted centrality features are then classified into two categories, creative (CRT) and non-creative (NCRT), employing a novel Capsule Graph Neural Network (CapsGNN). The uniqueness of the proposed classifier model lies in the utilization of a new activation function, Hyperbolic Tangent Exponential (TanhExp), designed to expedite the model's convergence rate. Furthermore, an attention module has been introduced to accentuate crucial information within the primary capsule layer, thereby enhancing the model's discriminative capabilities during the classification task. Additionally, a novel Sigsoftmax function-based dynamic routing algorithm has been incorporated into the classifier model to improve the coupling strength between the primary and higher capsule layers. Performance analysis and comparisons with existing algorithms underscore the superiority of the proposed classifier. Consequently, this innovative technique proves to be a valuable tool for identifying and recruiting creative individuals for various research-intensive sectors.

Computational creativity is defined as the ability of artificial systems to generate artifacts with substantial novelty and originality, comparable to those crafted by human experts. This study introduces an innovative approach to implementing computational creativity in the scientific domain, exemplified through the automatic generation of trigonometric identities using a novel LeakGAN model, a Generative Adversarial Network with leaked information. The novelty of the proposed LeakGAN lies in its discriminator model, constructed on the foundation of a Convolutional Neural Network (CNN), aimed at capturing the most relevant features from input data. These features are subsequently leaked to the generator model, enabling the production of identities with substantial originality and quality. The introduced novelty in the discriminator’s architecture encompasses the use of a new activation function called Mish, strategically employed to enhance the network's convergence rate and address over-fitting issues during training. Additionally, an attention layer is introduced to highlight the most relevant information within the feature space, thereby improving the network's learning capacity. Furthermore, a unique mixed pooling layer is utilized, combining the advantageous effects of max-pooling and average pooling operations to enhance the network's adaptability to varying feature distributions. Performance analysis, incorporating BiLingual Evaluation Understudy (BLEU) metrics and various comparative studies, substantiates the efficacy of the proposed LeakGAN model in generating novel identities compared to its traditional counterparts. Moreover, human evaluation involving 20 mathematical experts confirms the significant novelty of the generated identities compared to existing standard textbook problems. Consequently, the proposed technique proves valuable for generating diverse trigonometric identities suitable for inclusion as chapter-end exercises in middle school mathematics textbooks.

This paper proposes a generic architecture of a recurrent fuzzy inferential neural network realized with Petri Nets. The proposed recurrent topology allows revision or updates of fuzzy singleton memberships of inferences, which may lead to limit cycles (sustained periodic oscillations) or stability of fuzzy inferences. Determining stability in such recurrent fuzzy neural network requires adaptation of fuzzy memberships for all propositions mapped at places of the Petri Net in parallel. The network is said to have attained stability, if after$k$updates of memberships of the propositions, the steady-state values are reached for all the propositions of the network, where$k$denotes the number of transitions in the Petri net. If fuzzy memberships of the propositions do not converge after$k$updates, then the network yields sustained oscillations in memberships (called Limit Cycles). Detection of stability or limit cycles in such network requires users to wait for$k$steps of fuzzy membership updates at all places of the network. To avoid the computational overhead for$k$updating of memberships in the entire network, this paper makes an attempt to determine the condition of stability or limit cycles using Lyapunov stability theorem before the network is invoked for fuzzy membership updating and inference generation. The results of the analysis envisage that the condition of stability depends on the topological architecture and initial assignment of memberships at the places. The condition derived can be checked to test possible stability in the network. In case the condition for stability is not attainable, the network is expected to have limit cycles, which too can be detected without updating of memberships.

Pure 2D context-free grammar (P2DCFG) with an independent mode of array rewriting, was recently introduced and named as IP2DCFG. Here we consider a variant of IP2DCFG, called (l/u)IP2DCFG, by requiring rewriting of the leftmost (respy. uppermost) symbol in every row (respy. column) of an array, with the symbol having a rewriting rule in a given set of pure context-free rules. We introduce an array P system with (l/u)IP2DCFG kind of rules and array rewriting in its membranes. When two membranes are used in the array P system, the array generative power is increased compared to using a single membrane.

The human ability to infer others' intent is innate and crucial to development. Machines ought to acquire this ability for seamless interaction with humans. In this article, we propose an agent model for predicting the intent of actors in human–human interactions. This requiressimultaneous generation and recognition of an interactionat any time, for which end-to-end models are scarce. The proposed agent actively samples its environment via a sequence of glimpses. At each sampling instant, the model infers the observation class and completes the partially observed body motion. It learns the sequence of body locations to sample by jointly minimizing the classification and generation errors. The model is evaluated on videos of two-skeleton interactions under two settings: (first person) one skeleton is the modeled agent and the other skeleton's joint movements constitute its visual observation, and (third person) an audience is the modeled agent and the two interacting skeletons' joint movements constitute its visual observation. Three methods for implementing the attention mechanism are analyzed using benchmark datasets. One of them, where attention is driven by sensory prediction error, achieves the highest classification accuracy in both settings by sampling less than 50% of the skeleton joints, while also being the most efficient in terms of model size. This is the first known attention-based agent to learn end-to-end from two-person interactions for intent prediction, with high accuracy and efficiency.

Two well-known representations of Generalized Type-2 Fuzzy sets, such as the z-slice and the vertical slice, are prevalent in the literature. While the z-slice based model has shown promising performance in reasoning and control applications, the vertical slice based model, until this date, is restrictedly being used for reasoning with rules containing General type-2 propositions in the antecedent and Interval type-2 propositions in the consequent. This paper attempts to overcome this restriction by proposing a general framework for automated reasoning with rules containing Vertical Slice based General Type-2 propositions in both the antecedent and the consequent. Naturally, the inference is a Vertically Sliced General type-2 fuzzy set, which is type-reduced and then (type-1) defuzzified by a simple but elegant approach. The proposed Vertical slice based defuzzification is time-efficient in comparison to its z-slice based counterpart as the former requires type-1 centroidal defuzzification only in µ-u plane, while the latter requires Karnik-Mendel defuzzfication over each z-slice. The proposed vertical slice based reasoning and defuzzification has successfully been applied in angular position control of an inverted pendulum system. Experiments undertaken confirms that the proposed vertical slice based controller outperforms the existing z-slice, Interval type-2 plus KM/CKM defuzzification, and other control strategies with respect to the settling time, peak-overshoot, and root-mean square error.

The paper deals with functional brain-connectivity analysis between pairs of brain lobes for a given learning task by utilizing the fuzzy implication relations between the extracted signal features acquired from selected channels of the lobes. The Dienes-Rescher type fuzzy implication relation is chosen for its closest similarity with propositional implication, resembling implication in the true sense of its logical semantics. The Diens-Recher type implication has successfully been employed to check similarity in functional brain-connectivity for healthy (normal) children (below 2 years) in a learning task of fruits and animals. It is noted that children with Dyslexia disease exhibit different brain-connectivity patterns with respect to those of healthy subjects. This very finding opens up a new vista of research to recognize dyslexia patients from their healthy counterpart. Additionally, the k-means clustering algorithm is employed to cluster children suffering from Dyslexia into groups, based on their similarity in possible functional brainconnectivity. Such similarities of Dyslexia patients indicate commonality in wrong terminations of neural pathways, which is a well-known phenomenon in Dyslexia. The performance analysis undertaken reveals that the proposed fuzzy relational approach outperforms classical Granger causality, convergence crossmapping technique, probabilistic relative correlation adjacency matrix and transfer entropy approaches with respect to 2 metrics: modularity and average efficiency.

The industrial internet of things (IIoT) and Industry 4.0/5.0 enable the integration of machinery, equipment, processes, and humans across a variety of vertical sectors, including manufacturing and logistics supply chains, transportation, and medical care (Yadav et al., 2022). Several types of sensor nodes link these interconnected machines/appliances, sensing and transmitting data to the nodes or the cloud. To manage those links, next-generation networking technologies, such as 6G and Cybertwin, are being introduced. Sixth-generation (6G) communication will be critical in providing complex wireless interconnections, with 6G networks expected to be capable of supporting millions of linked devices and systems while maintaining high data rates and low latency (Kanwal et al., 2022). Blockchain is one emerging technology that can contribute to IIoT stability. Blockchain looks to offer a solution to maintain user privacy while still preserving the capacity for immutable information and replication. A blockchain technology is used to enforce a free distributed ledger to record transactions by peer-to-peer network nodes (P2Ps) and to avoid the need for a central authority through a distributed consensus process. This special issue focuses on six high-quality studies that address real-world issues in IIoT. Sharma et al. (2021) suggested a blockchain-based IoT architecture that uses the identity-based encryption (IBE) algorithm to improve the security of healthcare data. In this case, the smart contract outlines all of the fundamental processes of the healthcare system, which can benefit all stakeholders. Many tests are carried out in order to assess the efficacy of the suggested strategy. The findings reveal that the suggested system outperforms the current well-known strategies. Al-Haija et al. (2022) built a strong classifier for identifying and categorizing various cyberattacks in IoT networks using the AdaBoost machine learning algorithm paired with decision trees and substantial data engineering techniques. We test our system using the TON IoT 2020 datasets, which are a collection of datasets designed particularly for three-layered IoT systems that include physical, network, and application layers. We compare our system's performance to that of existing cutting-edge technologies. Our experimental results show that our framework is capable of offering improved classification accuracy and reduces kinds 1 and 2 mistakes for building more durable IoT infrastructures. Babu et al. (2022) introduced a unique IoT device authentication technique based on IBE and a blockchain network. Blockchain is utilized as a distributed PKG, removing the single point of failure and key escrow issue associated with PKGs. Furthermore, the suggested work is implemented on Hyperledger Fabric, an open-source blockchain platform that effectively handles the adding, updating, and deletion operations required for successful IoT device authentication and communication. Mehbodniya et al. (2022) created a framework for signature creation and verification using a modified Lamport Merkle Digital Signature technique. It employs a central healthcare controller (CHC) to determine the origin of the created signature as well as verification and authentication. To validate the signature, the validation hash public key with create key is necessary. When compared with conventional approaches, this resulted in more efficient, cost-effective, and speedier security. Vigneysh et al. (2022) provided a successful technique for increasing dynamic responsiveness during system uncertainties such as voltage distortions, frequency changes, renewable energy source variations, and the presence of non-linear and unbalanced loads. It also increases the quality of current fed into the grid during uncertainty. The suggested control approach is used to manage both the dc side capacitor voltage and the current loop of a grid-connected inverter. The suggested system is simulated in the MATLAB Simulink environment, and its performance is compared with that of standard controllers to demonstrate the efficacy of the proposed control technique during system anomalies. Patil et al. (2022) developed a two-phased technique for blockchain and IoT federated networks that use a multi-criteria-based approach to connection selection. The dynamic gateway scheduling technique is capable of supporting both blockchain-based transactions and IoT device connectivity. Furthermore, the suggested technique improves the fairness of data transfer for each gateway, resulting in efficient data transmission. Before using the link selection process, machine learning (ML) approaches are used to examine the state of the communication channels. The links are then selected using multi-criteria statistical approaches. Finally, scheduling is carried out in order to identify the best gateway for quickly channelling blockchain data.

Thisarticle deals with a simple indoor game, where the player has to pass a ball through a ring fixed on a variable pan-tilt platform. The motivation of the research is to learn the gaming actions of an experienced player by a robot arm for subsequent training to younger children (trainee) by the robot. The robot learns the gaming actions of the player at different game states, determined by pan-tilt orientations of the ring and its radial distance with respect to the player. The actions of the experienced player/expert are defined by six parameters: three junction-coordinates in the right arm of the player and the three-dimensional speed of the ball in a given throw. Reinforcement learning is employed here to adapt a state-action probability matrix (SAPM) of a probabilistic learning automaton based on the reward (or penalty) scores of the player due to the success (or failure) in passing the ball through a given ring. A hybrid brain-computer interface is used to detect the failures in the gaming action of the player by natural arousal of error-related potential (ErrP) signal following motor execution, indicated by motor imageries. In absence (presence) of ErrP after a motor imagination, the system considers a success (failure) in the player's trials, and thus adapts the probabilities in the learning automata according to success/failure of individual game instances. After the convergence of the SAPM, the same is used for planning, where the action corresponding to the highest probability at a given state in the automaton is selected for execution. The robot can autonomously train the game to the children using the learning automaton with converged probability scores. Experiments undertaken confirm that the success rate of the robot arm in the motor execution phase is very high (above 90%) when the ring is placed at a moderate distance of 4 feet from the robot.

The mobile traffic data and resources using IoE in wireless networking have raised numerous problems in terms of performance monitoring in edge-connected devices [1]. Next-generation networks, such as 6G and cybertwin, are implemented to address these problems. Sixth-generation (6G) communication would play a vital role in supporting complex wireless interconnectivity. In order to allow millions of connected devices and applications to operate smoothly at high data rates and low latency, a network of the 6G is anticipated [2]. The only access point for the Internet is cybertwin, which serves as a contact hub and tracks all user requirements. In the edge-cloud cyberspace, cybertwin is a digital database of smartphone activities, terminals, objects, etc. The integrated use of technology such as blockchain, 6G, and cybertwin is a multidisciplinary area for designing effective and efficient IoE systems [3]. The purpose of this Special Issue is to examine the new technology, innovative architectures, and future problems in depth in terms of network secured infrastructure based on cybertwin for 6G-enabled IoE.

Scientific creativity refers to the development of new and innovative ideas that foster technological growth and advancement. This paper attempts to identify creative individuals in scientific domain by evaluating their visuo-spatial reasoning ability using EEG analysis system. The main objective of the present work is achieved by first procuring EEG signals from the scalp of subjects involved in a mental paper folding task. The acquired signals are pre-processed and transformed into a topological map using correlation analysis to investigate the connectivity patterns amongst different brain lobes pertaining to different degrees of spatial abilities (high and low). The acquired brain networks depict strong interconnections amongst bilateral supramarginal gyrus, right anterior prefrontal and right superior temporal lobes for subject possessing high spatial skills. Since, the correlation based brain network analysis provides a qualitative illustration of the connectivity patterns, centrality induced quantitative analysis have been performed. Such an evaluation has been conducted using two categories of centrality measures viz. degree centrality and betweenness centrality. The results obtained from centrality analysis also infer the active involvement of the aforesaid brain regions during mental paper folding activity. Finally, the centrality based network features are transferred to a novel Capsule Graph Neural Network (CapsGNN) based classifier to categorize the desired class labels. Performance analysis undertaken confirms the superior functionality of the proposed network with respect to the conventional models. Moreover, statistical evaluation conducted also assures the supercilious performance of the proposed classifier. Thus, the present methodology can be utilized for recruiting creative individuals to different sectors of industries associated with innovation such as architecture, game designing and the like.

The paper proposes a novel extension of many objective optimization using differential evolution (MaODE). MaODE solves a many objective optimization (MaOO) problem by parallel optimization of individual objectives. MaODE involves N populations, each created for an objective to be optimized using MaODE. The only mode of knowledge transfer among populations in MaODE is the modified version of mutation policy of DE, where every member of the population during mutation is influenced by the best members of all the populations under consideration. The present work aims at further increasing the communication between the members of the population by communicating between a superior and an inferior population, using a novel migration strategy. The proposed migration policy enables poor members of an inferior population to evolve with a superior population. Simultaneously, members from the superior population are also transferred to the inferior one to help it improving its performance. Experiments undertaken reveal that the proposed extended version of MaODE significantly outperforms its counterpart and the state-of-the-art techniques.

The paper proposes a novel approach to adaptive selection of sample size for a trial solution of an evolutionary algorithm when noise of unknown distribution contaminates the objective surface. The sample size of a solution here is adapted based on the noisy fitness profile in the local surrounding of the given solution. The fitness estimate and the fitness variance of a sub-population surrounding the given solution are jointly used to signify the degree of noise contamination in its local neighborhood (LN). The adaptation of sample size based on the characteristics of the fitness landscape in the LN of a solution is realized here with the temporal difference Q-learning (TDQL). The merit of the present work lies in utilizing the reward-penalty based reinforcement learning mechanism of TDQL for sample size adaptation. This sidesteps the prerequisite setting of any specific functional form of relationship between the sample size requirement of a solution and the noisy fitness profile in its LN. Experiments undertaken reveal that the proposed algorithms, realized with artificial bee colony, significantly outperform the existing counterparts and the state-of-the-art algorithms.

During the past two decade researchers have been exploring the mechanism of object shape and depth perception using EEG and fMRI. However, the underlying cortical process of perceiving different object sizes from a constant visual distance has never been explored. This paper provides a novel understanding of relative object size classification based on direct measure of parieto-occipital hemodynamics using functional near infrared spectroscopy (fNIRS). The cortical response is recorded from subjects engaged in visual perception task of relative object size. The signal is preprocessed (artifact removal) for construction of 176 features, which are thus reduced to 22 features using particle swarm optimization (PSO) technique. The reduced features are subsequently fed into an interval type -2 fuzzy set to classify the perceived objects (based on the underlying hemodynamic data) into three different classes: LARGE, MEDIUM and SMALL. Experimental analysis shows that the proposed feature-selection and classification framework attain higher classification accuracy which reaches over 87% in the classification of large objects. Analysis, further undertaken to know the underlying neurovascular mechanisms, reveals a distinct dorso-ventral shift (shall-medium-to-large) in parieto-occipital hemodynamic load which can be observed from the topographic brain activation. The average activation shifts are measured as 73.35 degrees in the right hemisphere compared to 93.71 degrees in the left hemisphere. The experimental outcomes could provide a novel measure in cortical hemodynamic features based perception of object size. In future, it could provide justification towards the visually challenged persons with perceptual difficulties.

The paper introduces a novel technique for aesthetic quality assessment of an actor from her/his audio-visual clips using the acquired P200 and N400 EEG-responses of the experimental subjects. The P200 signal responds with high amplitude when the subject experiences a non-beautiful stimulus, whereas the N400 signal offers a high negativity for good tonal quality of the actor in the audio-visual stimulus. The synergy of small P200 amplitude and large N400 negativity jointly indicates good aesthetic quality of the actor present in the audio-visual stimulus. The intra/inter-subjective variations in the assessment of aesthetic quality are resolved using a General Type-2 Fuzzy Reasoning. The novelty of the present research lies in the design of the General Type-2 Fuzzy Reasoning algorithm for assessment of aesthetic quality from the measurement of peak power and total power in the selected band of the above two signals. Experiments undertaken confirm that the proposed technique outperforms the state-of-the art techniques when realized for the present application. Finally, the top-ranking stimuli are identified based on the average score of the aesthetic quality of the stimuli assessed by 30 subjects. The top-ranking stimuli may be utilized for psychological nourishment of mentally-challenged people. Statistical technique undertaken confirms the superiority of the proposed technique with its competitors.

Human behavior is a complex action which has provoked the thoughts of many people for a long time. However, very little about the cognitive aspect of an individual person's personality is known till the date. In order to differentiate people with significant differences in personality from their brain responses, we must at first be able to classify them based on their thought processes. From the viewpoint of classical ethics, people can broadly be classified into two main classes, namely, Categorical and Consequentialist. In this paper, we conduct several experiments where the subjects experience various ethical dilemmas and their ethical values in response to the presented stimuli are investigated through a question-answer session. The brain responses of the subjects are acquired using electroencephalography, which is then fed to an attention based parallel Convolutional Bi-directional Long Short-Term Memory (AConvBi-LSTM-NN) network with an ultimate aim to classify people into two above mentioned categories. Apart from the application point of view, the novelty of the paper lies in representing the EEG time-series into a sequence of multispectral 2D images which contain the spatial information of the acquired signal. The spectral information, along with the EEG time series (temporal information) are then used to train the proposed convolutional Bi-LSTM Network. The experimental results demonstrate promising results in classifying people based on their ethical values from their brain responses, with high classification accuracy. This provides scope for a new direction of research which can be further explored.

This paper intends to develop a novel methodology for modeling a mind-controlled type-writer system to cater the needs of individuals suffering from various communication related disorders. This objective is fulfilled by first capturing EEG signals from ten subjects involved in mental utterance of seven vowel sounds. The eLORETA analysis of the acquired signals confirms the involvement of occipital, parietal and prefrontal lobes for this cognitive activity. The procured signals undergo the process of feature extraction after eradication of artifacts and are transferred to a novel capsule network module for categorization of seven class labels. Performance analysis undertaken confirms the superlative behavior of the proposed classifier with respect to other standard ones. Moreover, statistical evaluation also assures the superior performance of the proposed classifier model. A coding scheme has also been proposed to signify the consonants by the coalescence of two vowel sounds segregated by a space. Thus, the proposed methodology can be effectively utilized as a mind controlled type writing system to serve the needs of disabled individuals. Additionally, this technique can also be used in certain military scenarios that demand non-verbal communication as a secure option and in various BCI based gaming applications.

Protein complexes play a very important role in biological processes. The identification of the proteins in the protein complex as well as the prediction of protein complexes which are hitherto anonymous will improve the understanding of the protein complexes and related biological processes. Most of the computational methods used to predict protein complexes were based on the principle that proteins inside the complex have more interactions. The protein-protein interaction (PPI) network is thus used to predict protein complexes. The features that affect the interaction of proteins in the protein-protein interaction network are mostly studied for identification of protein complexes. This paper is used to analyze the effect of the characteristic feature related to domains and functions on protein complex prediction. In this paper a ranking approach is applied to the solutions of differential evolution to identify protein complexes. The experimental results show that the proposed method beats the existing methods taking into consideration the typical performance metrics.

The paper proposes two novel extensions of the learning automata induced noisy bee colony (LANBC) to handle the presence of stochastic noise in the fitness landscape. The reward/penalty based reinforcement learning scheme of the stochastic learning automata (SLA) of LANBC helps a solution to prudently select a sample size for its periodic fitness evaluations based on the fitness variance in its local neighborhood. However, the LANBC suffers from two stalemates, including weak search dynamic in the presence of noise and the deterministic parental selection scheme leading to dismissal of quality solutions and loss of population diversity. The paper overcomes these impasses by employing two novel strategies. First, the search dynamic is amended with an aim to generate promising offspring solutions by appropriately tuning the control parameter based on the contamination effect of noise on other population members. Second, a modified probabilistic crowding induced niching behavior is introduced to promote quality solutions to the next generation to ensure both the population quality and the population diversity. Computer simulations undertaken on the noisy versions of a set of 28 benchmark functions reveal that the proposed algorithm outperforms its contenders with respect to function error value.

In this paper, we propose an image classification technique which uses a simple autoencoder with a regularizer. Nowadays, Convolutional Neural Networks (CNN) are primarily used for image classification. Our method can be used for image classification with much reduced requirement of computational capability than a complex CNN which has a huge number of degrees of freedom. Here, the terms simple and complex, respectively, correspond to the simplicity and the complexity of a network in terms of the number of learnable parameters (degrees of freedom) and the number of hidden layers. This technique uses features extracted from a pretrained CNN, trained on a completely different dataset. Genetic algorithm solves for the optimal hyperparameters of the pretrained CNN. It is observed that these features serve as important and robust parameters for the training of the autoencoder, as a final average image classification accuracy improvement of about 17.45% is observed with the inclusion of these features. We use a pretrained CNN on MNIST dataset and classify images of several other benchmark datasets. We utilize different classifiers for image classification based on features extracted from the autoencoder and repeat each of the experiments a number of times with different random initialization of the classifier and the weight matrix of the autoencoder. We also perform experiments by pretraining the CNN with different datasets. Our results show a notable image classification accuracy and a significant reduction of training time with respect to a complex CNN.

Differential Evolution algorithm is very challenging algorithm and has been found to put forth the basis of evolutionary computation. This algorithm because of its simple structure and linear nature, has been applied to a large number of optimization problems from various diversified fields. In this paper, we propose a new variant of DE by modifying the original LSHADE-cnEpSin algorithm. Two new modifications are proposed, keeping all the modifications of LSHADE-cnEpSin intact. The modifications proposed include the introduction of adaptive parameters by using Weibull distribution based scaling factor and exponentially decreasing crossover rate. Apart from that linearly decreasing population size is also used. The main reason for these adaptations is to make an adaptive algorithm so that no parameter needs to be changed from the end user perspective. The proposed algorithm has been applied to solve CEC2017 and CEC2019 benchmark problems. The numerical results prove that the newly proposed SALSHADE-cnEpSin algorithm performs better than SaDE, JADE, SHADE, LSHADE, CV1.0, CVnew, MVMO and other algorithms.

This paper addresses an interesting problem to model common spatial pattern (CSP) using an objective function employed to segregate EEG signals for a given cognitive task into two classes. The novelty of the present research is to include phase information with amplitude of the EEG signals to differentiate class boundaries. A new formulation of CSP is introduced and solved using Lagrange's multiplier method taking phase information of EEG into account. In addition, the proposed CSP is also realized with Schur Decomposition technique instead of using the conventional eigenvalue decomposition to overcome the disadvantage of using the latter one. Experiments undertaken confirm that the proposed phase-sensitive CSP and the CSP with Schur decomposition yield better performance than their non-phase sensitive counterpart by a large margin with respect to classification accuracy with the best results obtained by former CSP algorithm.

The proposed system aims at automatic identification of an unknown dance posture referring to the 34 primitive postures of ballet, simultaneously measuring the proximity of an unknown dance posture to a known primitive. A simple and novel seven stage algorithm achieves the desired objective. Skin color segmentation is performed on the dance postures, the output of which is dilated and edge is detected. From the boundaries of the postures, connected components are identified and the boundary is piecewise linearly approximated using modified artificial bee colony algorithm. Here, lies the novelty of our work. From the approximated boundary, features are extracted in terms of internal angles. This whole procedure is repeated for all the training images as well as testing image. The classification of the training image containing ballet posture is done using Euclidean distance matching.

The paper aims at classifying the learning-skill of driving-learners by utilizing the acquired P300 and N400 event related potentials during the learning phase of a simulated car-driving task. A set of driving stimuli, including braking on sudden appearance of bumpers, steering control at the sharp bending points, and the like, are prepared to experimentally classify the learning skill of the subjects in three distinct classes: Low, Medium and High. The complexity in classifying the subjective learning-skill arises because of intra- and inter-session variations in brain signals due to temporal fluctuation in activation levels of the involved brain lobes. A novel z-slice based model of general type-2 fuzzy set is proposed to represent the intra- and inter-session variations by the footprint of uncertainty and their composite variations by z-slices at different values of a given feature. Further, a novel technique for z-slice based classifier is proposed to classify the learning-skill under intra-and inter-session uncertainty. The proposed classifier is found to outperform traditional and well-known type-2 classifiers for the present learning-skill classification task in Experiments undertaken confirm the frontal and parietal theta (4-7 Hz) activation in discrete learning steps. The proposed research outcome may directly be utilized to certify driving learners with required learning skills.

We study the vowels detection from brain activation due to vowel sound imageries. At first we experimentally determine the maximum and relatively longer activation that takes place in the frontal or pre frontal lobe during vowel sound Imagination using acquired electroencephalographic signal analysis. Then we capture pre-frontal or frontal vowel sound imagery using a functional near infrared device to extract certain statistical features. Differential evolution based feature selection is used to for dimensionality reduction. The reduced feature set is then used to design an interval type 2 fuzzy classifier to classify the vowels from the pre frontal or frontal f-NIRs response to vowel sound imagination. Experiments undertaken confirm that the proposed classifier outperforms its competitors in classification accuracy for each vowel sound imagery class. They further confirm that the f-NIRs based classification outperforms EEG based modality for better capture of brain activations. Consonants are encoded with two vowel sounds with a space between them. Thus the proposed technique can effectively be used for mind driven type writing of vowels and consonants, serving people suffering from vocal deficiency.

We propose a novel approach to solve the many objective optimization (MaOO) problem using a ranking policy, instead of the Pareto ranking, supposing that a solution is unlikely to perform well for all objectives in a MaOO problem. A solution is thus evolved with respect to a specific objective only, which it may proficiently optimize. First, all objectives of the MaOO problem are individually optimized by evolutionary algorithms in parallel. The second step is concerned with judiciously selecting and filtering the quality solutions obtained by individual optimization of all objectives in parallel. A unique ranking policy is proposed to grade the members of the union set of quality solutions based on their extent of optimization of individual objectives. The evolutionary algorithm used for parallel optimization of all objectives in a MaOO here has been realized with differential evolution (DE). The mutation strategy of DE is also amended here with an aim to allow controlled communication between population members, concerned with parallel optimization of different objectives of a MaOO problem. Experiments undertaken with DTLZ and WFG test suits reveal that the proposed algorithm outperforms the state-of-art techniques with respect to inverted generational distance and hypervolume metrics.

We propose two extensions of the traditional artificial bee colony algorithm to proficiently optimize noisy fitness. The first strategy is referred to as stochastic learning automata induced adaptive sampling. It is employed with an aim to judiciously select the sample size for the periodic fitness evaluation of a trial solution, based on the fitness variance in its local neighborhood. The local neighborhood fitness variance is here used to capture the noise distribution in the local surrounding of a candidate solution of the noisy optimization problem. The second strategy is concerned with determining the effective fitness estimate of a trial solution using the distribution of its noisy fitness samples, instead of direct averaging of the samples. Computer simulations undertaken on the noisy versions of a set of 28 benchmark functions reveal that the proposed algorithm outperforms its contenders with respect to function error value in a statistically significant manner.

This paper presents a novel fuzzy based approach to gesture driven human robot interaction. Now a day, gestures are considered to be the most effective communicative medium for remotely controlling a robot. In this work, the gestures are employed to instruct a Khepera II robot to move from a specific starting position to a goal position following a specific path. The main highlight is the determination of exact degree of rotation with proper application of acceleration and brake in order to reach the specified goal position without hitting the obstacles. A Takagi-Sugeno-Kang based fuzzy model with two antecedents (type-2 fuzzy sets) and one consequent (crisp value) has been employed to determine the angle of rotation. The performance of the proposed framework has been tested in terms of a number of parameters like accuracy, precision, error rate etc. And in each case, the formulated strategy has proved its worth.

P300 is one of the most widely studied event-related potentials. Unfortunately, most of the existing automatic P300 detection schemes require computations over repetitive trials in both training and recognition phases. Several attempts have recently been endeavored towards the single trial detection of the P300 signals. However, no acceptable solution to the problem is found till date. In the present work, we have attempted to address this problem in the light of latency and (amplitude) deflection of the signal. The intra- and inter-personal variations inherent in these features are managed by the uncertainty management characteristics of General Type-2 Fuzzy Sets. First, these sets are constructed by exploiting the knowledge obtained from different trials of a large number of subjects. The secondary membership functions of the Type-2 Fuzzy Sets are computed based on a novel density dependent measure of the primary membership functions in the footprint of uncertainty. Second, recognition of P300 in an unknown EEG trial is performed based on the agreement of measured feature values with the General Type-2 Fuzzy knowledge-base. Majority voting of the concerned electrodes makes the scheme more robust. The experimental results show that the proposed algorithm is capable of achieving 88.60% accuracy in single trial detection of P300 instances, which is significantly higher than those obtained in state of the art algorithms.

Although there exist recent works on fMRI based cognitive learning, there is a dearth of literature on fNIRs based studies on learning and memory. This paper provides a novel study on the cognitive load detection of subjects engaged in symbol-meaning associative learning tasks from the direct measurement of the hemodynamic response of the brain. The hemodynamic response collected during symbol-meaning associative learning tasks by subjects are pre-processed (filtered from artifacts) for extraction of 112-dimensional features, which are reduced to 20 dimensions by a meta-heuristic optimization algorithm for subsequent transfer to a interval type-2 fuzzy classifier to classify three levels of cognitive loads (High, Low and Moderate) borne by the subjects at different time slots of the learning task. Analysis undertaken reveals that the type-2 fuzzy classifier with the proposed feature selection mechanism has a high performance in classification of the cognitive loads over 89%. Experimental analysis further reveals that the transfer of brain activation from orbitofrontal to ventrolateral prefrontal cortex takes place during transition of cognitive load from high to low. In addition, the activation of dorsolateral prefrontal cortex is also reduced during low cognitive load of subjects. These findings would offer justification of inability to handle high cognitive loads by people with under-developed/damaged orbitofrontal and dorsolateral prefrontal cortex.

The paper attempts to model human working memory using fuzzy relational equation with an aim to retrieve the relevant stored information in the memory from the partial input using the model. Psycho-physiological experiments have been developed to validate the model to match the model generated memory-response with the actual memory response using EEG signals acquired during memory encoding and recall phases. The fuzzy relational equation developed here represents brain connectivity in the fuzzy space between the encoding and the recall instances. The paper introduces a novel approach to compute inverse fuzzy relation with respect to max-min composition operator to determine the short-term memory information from the working memory, when the latter is stimulated with partial faces of people already encoded in the short-term memory. An error metric is defined to measure the error amplitude between the model-predicted encoding pattern and the actual pattern encoded in the short-term memory. A small value in error indicates a good accuracy of the proposed working memory model, and thus can be used to discriminate people with memory failure. Experiments undertaken reveal that the error metric could be used successfully to detect memory failures in five patients, two of which suffer from Parkinson, two from the early Alzheimer's disease and one from frontal lobe damage.

Currently, gesture recognition from continuous video sequences is one of the most exciting research areas. This paper proposes a novel HMM-based gesture recognition scheme that can be implemented for developing an improved HCI system capable of providing enhanced performance. This framework explores the high potential of Microsoft's Kinect sensor in gesture recognition by utilizing it in the data acquisition phase. The primary novelty of the work lies in the choice of an active difference signature-based feature descriptor that contains time-warped information in a single sequence over the classically used geometric features. The discussed framework has been tested for 12 distinct gestures embodied by 60 different subjects and it is important to note that for all the gestures the proposed scheme has attained a fairly high recognition rate of nearly 90% which proves the worth of the present work in real time applications. Further, to check the efficacy of the newly formulated framework the performance of the same has been validated against the existing standard technologies.

Multi-robot cooperation entails planning by multiple robots for a common objective, where each robot/agent actuates upon the environment-based on the sensory information received from the environment. Multi-robot cooperation employing equilibrium-based reinforcement learning is optimal in the sense of system resource (time and/or energy) utilization, because of the prior adaption of the environment by the robots. Unfortunately, robots cannot enjoy such benefit of reinforcement learning in presence of multiple types of equilibria (here Nash equilibrium or correlated equilibrium). In the above perspective, robots need to adapt with a strategy, so that robots can select the optimal equilibrium in each step of the learning. The paper proposes consensus-based multi-agent Q-learning to address the bottleneck of the optimal equilibrium selection among multiple types. An analysis reveals that a consensus (joint action) is coordination type pure strategy Nash equilibrium as well as pure strategy correlated equilibrium. The superiority of the proposed consensus-based multi-agent Q-learning algorithm over the traditional reference algorithms in terms of the average reward collection is shown in the experimental section. In addition, the proposed consensus-based planning algorithm is also verified considering multi-robot stick-carrying problem as a benchmark.

This paper formulates the protein-protein interaction (PPI) prediction problem as a multi-objective optimization (MOO) problem. The focus here is to jointly maximize i) the number of common neighbors of the proteins predicted to be interacting, ii) their functional similarity, and iii) the ratio between their individual accessible solvent area and that of the corresponding protein-protein complex. The above MOO problem is solved using a fusion of the differential evolution for multi-objective optimization and the stochastic learning automata. Experiments undertaken reveal that the proposed PPI prediction technique outperforms existing methods with respect to sensitivity, specificity, and F1 score.

Centrifugation is often applied in laboratories and industries to increase the effective gravity on a particle and hence make it sediment faster. Based on this principle, one may extend the existing optimization techniques, which are driven by only gravitational force (objective values of discovered best solutions), and do not consider application of centrifugal force for faster convergence. We extended the Nelder-Mead's simplex algorithm, by applying an exponentially decaying centrifugal force on each of the computed vertices of the simplex. The proposed centrifugation technique was also applied on other optimization algorithms including differential evolution and gravitational search algorithms. It was seen that application of centrifugal force indeed enhanced the objective values obtained by of all the tested evolutionary algorithms. The comparative performance of the extended Nelder-Mead Algorithm was found to be better among all the tested algorithms. The algorithms were compared on the basis of the best obtained objective value after a fixed number of objective function evaluations (here 20 times the problem dimension). Testing was performed in the real world problem of EEG feature selection (from brain networks), for the classification of memory encoding versus recall using SVM. The average classification accuracy was found to be high (89.97%).

This paper proposes a novel evolutionary approach to the optimal selection of electrodes as well as relevant EEG features for effective classification of cognitive tasks. The problem has been formulated in the framework of a single objective optimization problem with an aim to simultaneously satisfy three criteria. The first criterion deals with maximization of the correlation between the features of EEG sources before and after the selection of the optimal electrodes. The second criterion is concerned with minimization of the mutual information between the features of the selected EEG electrodes. The last criterion aims at maximization of the ratio of the difference between the selected features of the EEG sources between and within any two cognitive tasks. A self-adaptive variant of firefly algorithm is proposed to solve the above optimization problem by proficiently balancing the trade-off between the computational accuracy and the run-time complexity. Experiments undertaken over wide variety of cognitive tasks reveal that the proposed algorithm outperforms the other standard algorithms (applied to the same problem) in terms of accuracy and computational overhead.

In this paper, a novel Static Learning (SL) strategy to adaptively vary swarm size has been proposed and integrated with Particle Swarm Optimization algorithm. Besides, the whole population has been divided into two sub swarms, where particles of different sub swarms interact within their neighbourhood and the existence of better particle is determined by evaluating its survival probability. Proper resource based particle replacement scheme and a linear chaotic term has also been included to ensure preservation of diversity of the swarm. In addition, the PSO algorithm is divided into two phases, with relevant algorithmic modification for each phase. The first phase is assigned to focus solely on better exploration of the search space. The second phase focuses on better utilization of the explored information. The proposed Static Learning Particle Swarm Optimization with Enhanced Exploration and Exploitation using Adaptive Swarm Size (SLPSO) algorithm is tested on a set of shifted and rotated benchmark problems and compared with six other recent state-of-the-art PSO algorithms. The proposed (SLPSO) algorithm demonstrates superior performance over other PSO variants.

The paper aims at solving a multi-robot box-pushing problem in the presence of noisy sensory data using evolutionary algorithm. In the box-pushing problem by twin robots, the range data obtained by the robots at any instant of time are measurements, and the torque and/or force to be developed by the robots for a local movement of the box are estimators. We here use torques and forces developed by the robots to construct two objectives on minimization of the total energy consumed and the total time required for a local movement of the box in the presence of noisy sensory data. The box-pushing problem is solved using the proposed extended version of the noisy non-dominated sorting bee colony (ENNSBC) algorithm to handle noise in the objective surfaces. Experiments undertaken in both simulation and real-world platforms reveal the superiority of the proposed ENNSBC to other competitor algorithms to solve the box-pushing problem with respect to the performance metrics defined in the literature.

This work demonstrates an interesting approach to gesture recognition for elderly people for the purpose of health monitoring at home. The system proposes to detect disorder symptoms on the basis of gesture analysis and generate alarms, thereby finding significance in elderly healthcare. Here the gestures are tracked using Microsoft's Kinect sensor. From each frame captured by the Kinect sensor, four centroids representing four parts of the body are calculated and from these four centroids a novel feature set is extracted in terms of Euclidean distances and angles. We have noticed that for different persons' body types the extracted features might vary. Thus to accommodate these non-uniformities, we have used the concept of interval type-2 fuzzy logic based classification. The unknown gesture is recognized based on matching with all the known gestures from the dataset. The proposed methodology provides a high accuracy rate of 92.14%.

The main notion of this paper is to identify the cognitive load during a mental arithmetic task experiment using fNIRS signals. The first objective is to classify the difficulty level and the state of inactivity during the given task. To identify the classes, the feature vectors have to undergo all the possible steps of a pattern classification problem. In this paper, we have developed a novel Feature Selection technique to reduce the dimension of the feature vectors by omitting the redundant features. For this purpose, an objective function depending upon the class density or likelihood functions is optimized using the well-known Differential Evolution algorithm. General type-2 fuzzy classifier is used for subsequent classification step. The proposed Feature Selection technique gives a satisfactory accuracy results over principal component analysis. The fuzzy classifier outperforms the other well-known classifier like support vector machine, k-nearest neighborhood. Experimental result reveals that the proposed likelihood-based FS induced type 2 fuzzy classifier attains the highest classification accuracy (above 90% in each case) as compared to its standard competitors. The load of a subject undergoing the experiment is measured at a particular class relying upon the mean type- 1 fuzzy value of all feature entities. A clear discrimination in concentration level from 16 channels has been observed for each distinct feature set.

In this paper, a novel multi-stage approach to knowledge extraction from a time-series is proposed. A given time-series is modeled as a sequence of well-known primitive patterns with the purpose of identifying first-order probabilistic transition rules for prediction. The first stage of the proposed model segments a time-series into structurally distinct temporal blocks of non-uniform length such that each block possesses a relatively low variation of dynamic slope. In the second stage, the temporal segments thus obtained are normalized and matched with one of four well-known primitive patterns using a fuzzy matching algorithm. Finally, the sequence of matched segments is used to represent the time-series as a set of four directed graphs corresponding to the four primitive patterns. Each vertex in the graphs represents a horizontal partition of the time-series and each directed edge indicates the transitions between two such partitions caused by the occurrence of one or more temporal segments. In the test phase, the graphs are employed to predict possible future values of the time-series. Experiments carried out on the TAIEX close-price time-series indicate a high prediction accuracy, thereby validating the use of the model for real-life forecasting applications.

With the growing interest in the domain of human computer interaction (HCI) these days, budding research professionals are coming up with novel ideas of developing more versatile and flexible modes of communication between a man and a machine. Using the attributes of internet, the scientists have been able to create a web based social platform for learning any desired art by the subject himself/herself, and this particular procedure is termed as electronic learning or e-learning. In this paper, we propose a novel application of gesture dependent e-learning of dance. This e-learning procedure may provide help to many dance enthusiasts who cannot learn the art because of the scarcity of resources despite having great zeal. The paper mainly deals with recognition of different dance gestures of a trained user such that after detecting the discrepancies between the gestures shown and actually performed by a novice; the user can rectify his faults. The elementary knowledge of geometry has been employed to introduce the concept of planes in the feature extraction stage. Actually, five planes have been constructed to signify major body parts while keeping the synchronous parts in one unit. Then four distances and four angular features have been obtained to provide entire positional information of the different body joints. Finally, using a probabilistic neural network the dance gestures have been classified after training the said network with sufficient amount of data recorded from numerous subjects to maintain generality.

Patients with prosthesis defects find it is very difficult to perform day-to-day basic tasks which involve employment of their limbs. This motivates us to develop a system where an artificial limb is employed to mimic the arm gestures of the patients for assisting them. Towards developing this system, we have taken the help from the electroencephalography (EEG) signals acquired from the brain of the patients to build a bypass network (BPN) to direct the artificial limb. Since difficulties are already present in the arm movements of the patients (here subjects), thus only gestures of those subjects are not sufficient to build the proposed system. This research finds tremendous applications in rehabilitative aid for the disable persons. To concretize our goal we have developed an experimental setup, where the target subject (for training phase healthy subjects are taken into account) is asked to catch a ball while his/her brain (occipital, parietal and motor cortex) signals using EEG acquisition device and body gestures using Kinect sensor are simultaneously acquired. These data are mapped using four cascade-correlation learning architecture (CCLA) to train artificial limb (we have used Jaco robot arm) to move accordingly. Utilizing the mapping results obtained from these four CCLAs, a BPN is developed. When a rehabilitative patient is unable to catch the ball, then in that scenario, the artificial limb is helpful for assisting the patient to catch the ball with a high accuracy of 85.65%. The proposed system can be implemented not only for ball catching experiment but also in several applications where an artificial limb needs to perform a locomotive task based on EEG and body gesture.

EEG based vowel classification is currently gaining importance for its increasing applications in the next generation mind-driven type-writing. This paper addresses a novel approach to classify the mentally uttered alphabets in a specific three lettered format, where the first and the last letter represent two vowel sounds and the middle is a space, where no character is imagined. Such formatting helps recognizing 26 alphabets in English language using seven vowel sounds only. To eliminate the possible infiltration of noise by parallel thoughts we used a specialized neuro-fuzzy classifier, where the first layer of the classifiers realized with fuzzy logic eliminates the possible creeping of noise due to side active channel interference. Two models of fuzzy preprocessing are used. The first one is realized with type-1 fuzzy logic, whereas the second model is realized with interval type-2 fuzzy sets. The latter model can take care of both intra- and inter-personal level uncertainty in measurements. Experiments undertaken reveal that the proposed type-2 fuzzy classifier outperforms both type-1 and traditional neural classifiers by a significant margin.

Protein-Protein Interactions (PPIs) play an important role in various cellular processes. This paper attempts to solve the PPI prediction problem in a multi-objective optimization framework. The scoring functions for the trial solution deal with simultaneous minimization of functional dissimilarity, intra- as well as inter-molecular energy and the difference in phylogenetic profiles of interacting proteins. The above optimization problem is solved using Firefly Algorithm with Non-dominated Sorting. The proposed technique outperforms existing methods, including gene-ontology based Relative Specific Similarity, Fuzzy SVM, phylogenetic profile and evolutionary/swarm algorithm based approaches, with respect to sensitivity, specificity and F1 score.

A novel multi-objective optimization algorithm is introduced in the paper to proficiently obtain Pareto-optimal solutions in the noisy fitness landscapes. First, a non-linear functional relationship between the fitness variance in the local neighborhood of a trial solution and the sample size for its periodic fitness evaluation is proposed. The second strategy is concerned with determining defuzzified centroidal value of the noisy fitness samples, instead of their conventional averaging, as the effective fitness measure of the trial solutions. Finally, to ensure the diversity of quality solutions in the noisy fitness landscapes, a new selection criterion induced by the crowding distance measure and the distribution pattern of noisy fitness samples is formulated. Experiments undertaken to validate the performance of the extended algorithm affirm its superiority to its contenders with respect to hyper volume ratio, when examined on a test suite of 23 standard benchmarks contaminated with additive noise of five statistical distributions.

Automatic person recognition problem draws significant popularity in the last decade in the field of human-robot interaction. This paper introduces a novel approach to identify a person automatically whom the robot has already met, based on its walking pattern as gait is a unique characteristic for every individual. Here, the Kinect sensor is used to record the gait pattern of a person by storing 20 3-D joint coordinates in each time stamps. The features like joint angle and joint length are obtained from each complete walk cycle. Among all these features, most significant features are selected using principal component analysis. Later, these features are fuzzified constructing a Gaussian membership function with the mean and standard deviation of each feature at different gait cycle. An Interval Type-2 membership is constructed with all these membership values for a particular feature in different trials. 10 walking data set of 10 subjects are processed here. Now, when any person out of these 10 persons is walking in front of Kinect, features are calculated. But as more than one feature value for a particular feature (each feature corresponds to each gait cycle in a complete walking task) is obtained, mean of all these values for a particular feature is considered as measurement point. Defuzzification is done using t-norm and average operators. The person corresponding to highest defuzzified value is considered as the unknown person. The classification accuracy is 89.667%. The proposed method is also compared with few existing person identification techniques and the results obtained prove the superiority of the proposed algorithm.

The recently developed Kinect sensor has opened a new horizon to Human-Computer Interface (HCI) and its native connection with Microsoft's product line of Xbox 360 and Xbox One video game consoles makes completely hands-free control in next generation of gaming. Games that requires a lot of degree of freedoms, especially the driving control of a car in racing games is best suitable to be driven by gestures, as the use of simple buttons does not scale to the increased number of assistive, comfort, and infotainment functions. In this paper, we propose a Mamdani type-I fuzzy inference system based data processing module which effectively takes into account the dependence of actual steering angle with the distance of two palm positions and angle generated with respect to the sagittal plane. The FIS output variable controls the duration of a virtual “key-pressed” event which mocks the users pressing of actual keys assigned to control car direction in the original game. The acceleration and brake(deceleration) of the vehicle is controlled using the relative displacement of left and right feet. The proposed experimental setup, interfacing Kinect and a desktop based racing game, has shown that the virtual driving environment can be easily applied to any games belonging to this particular genre.

Among different machine learning algorithms AdaBoost is a classification technique, which improves the classification accuracy by increasing the weights of the misclassified data. To overcome the problem of misclassification in Real AdaBoost algorithm, of the already classified samples, concept of margin is employed in the Parameterized AdaBoost algorithm. The new parameter, introduced in Parameterized AdaBoost, corresponding to the margin is chosen randomly between 0 to 1. However, the margin value is different for different classification problem. Hence, in this paper, the parameter corresponding to the margin is adapted by learning the parameter value with the help of Differential Evolutionary algorithm corresponding to the optimal classification accuracy. Experiment for the support of the proposed Adaptive Parameterized AdaBoost Algorithm has been conducted with different standard database given by UCI Machine Learning Repository. In addition, an application of Adaptive Parameterized AdaBoost is performed in EEG Motor Imagery Classification. Finally the EEG Motor Imagery Classified data (Left/Right) is tested in a robot.

The memory network is a result of current dipoles created in the brain. Localizing the source of these current flows is known as source localization, and it could potentially reveal which parts of the brain are actually responsible for a particular brain activity. It would also increase the spatial resolution of an EEG recording by identifying the true source of multiple correlated readings. In our experiments, we employed memory networks to classify perception of emotional instances conveyed in facial expressions as well as to localize sources. These networks were created by selectively evaluating EEG channel signals pairwise for Granger causality. Channel selection was based on clustering of EEG features by Self Organizing Feature Map (SOFM). Principal Component Analysis (PCA) was employed for dimension reduction and noise elimination of EEG features. Finally a new metric based on Fischer's discriminant was used to compare different source localization techniques, where real source locations are unknown. The perception of the stimuli was classified as belonging to one the following classes i) Happy ii) Sad iii) Fear iv) Relaxed. The created memory networks could classify perception of emotional content in 90.64% of cases. Comparison by the proposed Fischer Discriminant based metric revealed that the proposed network identification technique performs better at source localization as compared to independent component based source localization.

This paper introduces a novel approach to examine the scope of touch perception as a possible modality of treatment of patients suffering from certain mental disorder using a Radial Basis function induced Back Propagation Neural Network. Experiments are designed to understand the perceptual difference of schizophrenic patients from normal and healthy subjects with respect to four different touch classes, including soft touch, rubbing, massaging and embracing and their three typical subjective responses such as pleasant, acceptable, and unpleasant. Experiments undertaken indicate that that the frontal part of the scalp map of healthy subjects carry more blood during touch perception than those obtained for the schizophrenic patients. Further, for normal subjects and schizophrenic patients, the average percentage accuracy in classification of all the three classes including pleasant, acceptable or unpleasant is comparable with their respective oral responses. In addition, for schizophrenic patients, the percentage accuracy for acceptable class is very poor of the order of below 10%, which for normal subjects is quite high (46%). Performance analysis reveals that the proposed classifier outperforms its competitors with respect to classification accuracy in all the above three classes. A well known statistical test confirms that the proposed classifier outperforms all its competitors along with principal component analysis as feature selector by a large margin.

This paper proposes novel algorithms for data-point and feature selection of motor imagery electroencephalographic signals for classifying motor plannings involved in car- driving including braking, acceleration, left steering control and right steering control. Variants of neural network classifiers such as linear support vector machines, and kernel-based support vector machines including radial basis function kernel, polynomial kernel and hyperbolic kernel have been applied to classify the various cognitive tasks. Experimental finding reveals that the proposed data-point and feature selection technique altogether provides better classification accuracies (more than 88%) for all cognitive tasks in comparison with using factor analysis for data-point reduction and feature selection. It is also observed that power spectral density and discrete wavelet transform features are selected among the list of electroencephalographic features for holding the top two rank values for cognitive task classification during car-driving. From the experimental result, it is confirmed that support vector machines with radial basis function along with power spectral density outperforms the remaining feature-classifier pairs in terms of average classification accuracy.

This paper provides a novel approach to predict the Protein-Protein Interaction (PPI) network using a modified version of the Bat Algorithm. The attractive trait of the proposed approach is that it attempts to analyze the impact of physicochemical properties, structural features and evolutionary relationship of proteins, to predict the PPI network. Computer simulations reveal that our proposed method effectively predicts the PPI of Saccharomyces Cerevisiae with a sensitivity of (0.85) and specificity of (0.87) and outperforms other state-of-art methodologies.

The present work introduces a proposed Artificial Bee Colony with Adaptive Scale Factor (ABC-ASF) optimization algorithm-based optimal electrode selection strategy from which the acquired EEG signals enlighten the major brain activities involved in a cognitive task. In ABC-ASF, the scale factor for mutation in traditional Artificial Bee Colony is self adapted by learning from the previous experiences. Experimental results obtained from the real framework of estimating optimal electrodes indicate that the proposed algorithm outperforms other state-of-art techniques with respect to computational accuracy and run-time complexity.

The paper aims at designing new strategies to extend traditional Non-dominated Sorting Bee Colony algorithm to proficiently obtain Pareto-optimal solutions in presence of noise on the fitness landscapes. The first strategy, referred to as adaptive selection of sample-size, is employed to balance the trade-off between accurate fitness estimate and computational complexity. The second strategy is concerned with determining statistical expectation, instead of conventional averaging of fitness-samples as the measure of fitness of the trial solutions. The third strategy attempts to extend Goldberg's approach to examine possible placement of a slightly inferior solution in the optimal Pareto front using a more statistically viable comparator. Experiments undertaken to study the performance of the extended algorithm reveal that the extended algorithm outperforms its competitors with respect to four performance metrics, when examined on a test-suite of 23 standard benchmarks with additive noise of three statistical distributions.

This paper proposes a new classification algorithm which aims at predicting different states from an incoming non-stationary signal. To overcome the failure of standard classifiers at generalizing the patterns for such signals, we have proposed an Interval Type-2 Fuzzy based Adaptive neural fuzzy Inference System (ANFIS). Through the introduction IT2F system, we have aimed at improving the uncertainty management of the fuzzy inference system. Besides that using DE in forward and backward pass and improving the forward pass function we have improved the parameter update on wide range of nodal functions without any quadratic approximation in forward pass. The proposed algorithm is tested on a standard electroencephalography (EEG) dataset and it is noted that the proposed algorithm performs better than other standard classifiers including the classical ANFIS algorithm.

Damage in parietal and/or motor cortex of the brain can lead to inability in proper visuo-motor coordination, hampering movement planning and execution. The objective of this work is to predict joint coordinates of hand by sequential prediction of the parietal and motor cortex Electroencephalogram (EEG) features from their occipital counterparts using artificial neural networks (ANNs). EEG signals during hand movement execution are acquired from occipital, parietal and motor cortical regions and the joint coordinates of hand are acquired using Kinect sensor. The acquired EEG signals are preprocessed followed by extraction of wavelet features and selection of the best features using Principal Component Analysis. The EEG features originating from one brain region are mapped to the features of another brain region using regression analysis on artificial neural networks with Back Propagation learning. The mapped motor cortical EEG signals are finally used to predict the hand joint coordinates using Back Propagation learning based ANN. The performances of various weight adaptation techniques for Back Propagation learning are evaluated. Regression analysis results indicate that Levenberg-Marquardt optimization based weight adaptation performed best in terms of mean squared error, slope of the best linear fit and correlation coefficient between the original values and predicted results.

Neuroscientists usually determine similarity between EEG electrode signals, by a measure of pairwise linear dependence among them. However, recent research indicates the drawbacks of analyzing the pairwise dependence of signals instead of analyzing the simultaneous joint interdependence among them. To overcome this problem we propose a novel similarity measure known as probabilistic relative correlation. Our approach is unique because our similarity measure allows the electrodes to have probabilistic similarity measures and recognizes emotion dependent structures even from mismatched sequences of correlation. We further validate our proposed similarity measure by testing it on the well-known emotion recognition problem. Our experiments have noteworthy implications towards realizing the neural signatures of discrete emotions and will allow for the better understanding of neurological pathways associated with different emotional states. To identify the most active neurological pathways in brain during an emotion, we adapt the minimal spanning tree algorithm.

The paper proposes a solution to reduce accidents in driving by alarming specific cognitive failures to the drivers on occurrence of the failures. Three different types of cognitive failures that might occur due to lapse of i) visual alertness, ii) cognitive planning and iii) motor execution are studied, and suitable classifiers have been employed to classify these failures. Force exerted by the driver during turning or sudden tracking is also measured to detect his level of cognitive load during significant changes in the driving environment. Recurrent neural networks are introduced here as classifiers to decode cognitive tasks performed by the driver from his acquired EEG. For each recurrent neural net, we use a Lyapunov energy surface the minima of which denote the cognitive tasks during one of three cognitive activities mentioned above. Given the features of the measured EEG for a cognitive tasks, the recurrent net converges to one of several optima, describing a specific cognitive failure. Experimental results obtained by employing a driving simulator and an EEG system are encouraging.

A recurrent neural network model is designed to classify (pretrained) aromatic stimuli and discriminate noisy stimuli of both similar and different genres, using EEG analysis of the experimental subjects. The design involves determining the weights of the selected recurrent dynamics so that for a given base stimulus, the dynamics converges to one of several optima (local attractors) on the given Lyapunov energy surface. Experiments undertaken reveal that for small noise amplitude below a selected threshold, the dynamics essentially converges to fixed stable attractor. However, with a slight increase in noise amplitude above the selected threshold, the local attractor of the dynamics shifts in the neighborhood of the attractor obtained for the noise-free standard stimuli. The other important issues undertaken in this paper include a novel algorithm for evolutionary feature selection and data-point reduction from multiple experimental EEG trials using principal component analysis. The confusion matrices constructed from experimental results show a marked improvement in classification accuracy in the presence of data point reduction algorithm. Statistical tests undertaken indicate that the proposed recurrent classifier outperforms its competitors with classification accuracy as the comparator. The importance of this paper is illustrated with a tea-taster selection problem, where an olfactory perceptual-ability measure is used to rank the tasters.

This paper aims to design new strategies to extend traditional multiobjective optimization algorithms to efficiently obtain Pareto-optimal solutions in presence of noise on the objective surfaces. The first strategy, referred to as adaptive selection of sample size, is employed to balance the tradeoff between quality measure of fitness and run-time complexity. The second strategy is concerned with determining statistical expectation, instead of conventional averaging, of fitness samples as the measure of fitness of the trial solutions. The third strategy attempts to extend Goldberg's method to compare slightly worse trial solutions with its competitor by a more statistically viable comparator to examine possible placement of the former solution in the Pareto optimal front. The traditional differential evolution for multiobjective optimization algorithm has been modified by extending its selection step with the proposed strategies. Experiments undertaken to study the performance of the extended algorithm reveal that the extended algorithm outperforms its competitors with respect to three performance metrics, when examined on a test suite of 23 standard benchmarks with additive noise of three statistical distributions. The extended algorithm has been applied on the well known box-pushing problem, where the forces and torques required to shift the box by two robots are evaluated to jointly satisfy the conflicting objectives on task-execution time and energy consumption in presence of noise on range estimates from the sidewalls of the workspace. The application justifies the importance of the proposed noise-handling strategies in practical systems.

The paper addresses a novel approach to protein-ligand docking problem using Non-dominated Sorting Bee Colony optimization algorithm. In this work, protein- ligand docking is formulated as a multi-objective optimization problem. The docking energy, molecular weight and oral bioavailability are used as three scoring functions for the solutions. Results are demonstrated for six different target proteins both numerically and pictorially. Experimental results reveal that the proposed method outperforms Multi-Objective Particle Swarm Optimization, Non-dominated Sorting Genetic Algorithm-II and Artificial Bee Colony based ligand design method considering the three objectives of the evolved molecules.

An adaptive memetic algorithm incorporates an adaptive selection of memes (units of cultural transmission) from a meme-pool to improve the cultural characteristics of the individual member of a population-based search algorithm. The paper proposes an extension of Multi-objective Optimization realized with Differential Evolution algorithm by utilizing the composite benefits of Differential Evolution for Multi-objective Optimization (DEMO) for global search and Templocal refinementoral Difference Q-Learning (TDQL) for local refinement. Computer simulations performed on a well known set of 23 benchmark functions reveal that the proposed algorithm outperforms its competitors with respect to inverted generational distance, spacing and error ratio.

This paper provides a novel approach to design an Adaptive Firefly Algorithm using self-adaptation of the algorithm control parameter values by learning from their previous experiences in generating quality solutions. Computer simulations undertaken on a well-known set of 25 benchmark functions reveals that incorporation of Q-learning in Firefly Algorithm makes the corresponding algorithm more efficient in both runtime and accuracy. The performance of the proposed adaptive firefly algorithm has been studied on an automatic motion planing problem of nonholonomic car-like system. Experimental results obtained indicate that the proposed algorithm based parking scheme outperforms classical Firefly Algorithm and Particle Swarm Optimization with respect to two standard metrics defined in the literature.

This work aims at designing a fuzzy matching algorithm that would automatically recognize an unknown ballet posture from seventeen fundamental ballet dance primitives. A novel and simple 7-stage system is proposed to achieve the desired objective. Minimized skeletons of the dance postures are generated after performing skin color segmentation on them. Straight line approximation on the minimized skeletons with the help of chain code and sampling generate their equivalent stick figure diagrams. Significant straight lines from the stick figure diagrams are considered, their fuzzy membership with respect to the 4 quadrants are evaluated. Finally with the help of the evaluated data, a fuzzy T-norm operator determines the proximity of a generated dance posture with the seventeen fundamental dance primitives.

The paper provides a novel approach to emotion recognition of subjects from the user-specified word description of their facial features. The problem is solved in two phases. In the first phase, an interval type-2 fuzzy membership space for each facial feature in different linguistic grades for different emotions is created. In the second phase, a set of fuzzy emotion-classifier rules is instantiated with fuzzy word description about facial features to infer the winning emotion class. The most attractive part of this research is to autonomously transform user specified word descriptions into membership functions and construction of footprint of uncertainty for each facial feature in different linguistic grades. The proposed technique for emotion classification is very robust as it is sensitive to changes in word description only rather than the absolute measurement of features. Besides it offers a good classification accuracy of 87.8% and thus comparable with existing techniques.

Traditional approaches to fuzzy reasoning usually employ Generalized Modus Ponens to generate fuzzy inferences from a given set of fuzzy rules and observations. These observations act as instantiations for the fuzzy propositions present in the antecedent of the rule to infer the fuzzy proposition present in the consequent of the same rule. Unfortunately, in many real world problems, such as system diagnosis, one excluding all fuzzy propositions present in both antecedent and consequent of a rule are instantiated with fuzzy observations, but the rule cannot fire as there is no formalism to handle the situation. This paper proposes a logical basis to handle the above problem both in propositional and fuzzy reasoning systems. It has been shown that two rules are equivalent, where the second is constructed by transposition of one or more propositions of the first rule to the other side of the implication with changed sign. This property has been used here to develop the basis of (ad hoc) reasoning. In case of a fuzzy system comprising chain rules, selection of the firing order of rules using the above property is not easy. An algorithm for ad hoc reasoning for chained fuzzy system is proposed to take care of the complexity in testing the firing condition of chained rules and thereby determining their order of firing. Lastly, a Petri like net has been used as the basic structure of the reasoning system, which takes away the complexity in rule firing and firing order selection for chained rules.

In this paper, a novel design method of Generalized Type-2 Fuzzy Set (GT2FS) is proposed. The GT2FS involves the secondary memberships for individual primary membership curve, which is obtained here by formulating and solving an optimization problem. To accomplish this, we have used Differential Evolution. The secondary membership of a given source, symbolizing the consistency in its primary membership assignment, is determined with respect to the composite of all the users' primary membership functions. The performance of the proposed method of secondary membership evaluation has also been studied on an emotion recognition problem.

The paper proposes a novel approach to recognize smell stimuli from the electroencephalogram (EEG) signals acquired during the period of inhalation. The main contribution of the paper lies in feature selection by an evolutionary algorithm and pattern classification by Differential Evolution induced Hopfield neural network. One additional merit of the work lies in data point reduction by Principal component analysis. Experiments undertaken on 25 subjects with 10 smell stimuli indicate that the proposed scheme of feature selection, data point reduction and classification outperforms the traditional approach by a wide margin. Experimental results confirm that the smell stimuli excites the pre frontal lobe of the human brain and is responsible for a special type of brain rhythms (EEG signal) in alpha-band, theta-band and delta-band.

Facial expressions of a person representing similar emotion are not always unique. Naturally, the facial features of a subject taken from different instances of the same emotion have wide variations. In the presence of two or more facial features, the variation of the attributes together makes the emotion recognition problem more complicated. This variation is the main source of uncertainty in the emotion recognition problem, which has been addressed here in two steps using type-2 fuzzy sets. First a type-2 fuzzy face space is constructed with the background knowledge of facial features of different subjects for different emotions. Second, the emotion of an unknown facial expression is determined based on the consensus of the measured facial features with the fuzzy face space. Both interval and general type-2 fuzzy sets (GT2FS) have been used separately to model the fuzzy face space. The interval type-2 fuzzy set (IT2FS) involves primary membership functions for m facial features obtained from n-subjects, each having l-instances of facial expressions for a given emotion. The GT2FS in addition to employing the primary membership functions mentioned above also involves the secondary memberships for individual primary membership curve, which has been obtained here by formulating and solving an optimization problem. The optimization problem here attempts to minimize the difference between two decoded signals: the first one being the type-1 defuzzification of the average primary membership functions obtained from the n-subjects, while the second one refers to the type-2 defuzzified signal for a given primary membership function with secondary memberships as unknown. The uncertainty management policy adopted using GT2FS has resulted in a classification accuracy of 98.333% in comparison to 91.667% obtained by its interval type-2 counterpart. A small improvement (approximately 2.5%) in classification accuracy by IT2FS has been attained by pre-processing measurements using the well-known interval approach.

This paper provides a new deterministic Q-learning with a presumed knowledge about the distance from the current state to both the next state and the goal. This knowledge is efficiently used to update the entries in the Q-table once only by utilizing four derived properties of the Q-learning, instead of repeatedly updating them like the classical Q-learning. Naturally, the proposed algorithm has an insignificantly small time complexity in comparison to its classical counterpart. Furthermore, the proposed algorithm stores the Q-value for the best possible action at a state and thus saves significant storage. Experiments undertaken on simulated maze and real platforms confirm that the Q-table obtained by the proposed Q-learning when used for the path-planning application of mobile robots outperforms both the classical and the extended Q-learning with respect to three metrics: traversal time, number of states traversed, and 90° turns required. The reduction in 90° turnings minimizes the energy consumption and thus has importance in the robotics literature.

Memetic algorithms (MAs) are population-based meta-heuristic search algorithms that combine the composite benefits of natural and cultural evolutions. An adaptive MA (AMA) incorporates an adaptive selection of memes (units of cultural transmission) from a meme pool to improve the cultural characteristics of the individual member of a population-based search algorithm. This paper presents a novel approach to design an AMA by utilizing the composite benefits of differential evolution (DE) for global search and Q-learning for local refinement. Four variants of DE, including the currently best self-adaptive DE algorithm, have been used here to study the relative performance of the proposed AMA with respect to runtime, cost function evaluation, and accuracy (offset in cost function from the theoretical optimum after termination of the algorithm). Computer simulations performed on a well-known set of 25 benchmark functions reveal that incorporation of Q-learning in one popular and one outstanding variants of DE makes the corresponding algorithm more efficient in both runtime and accuracy. The performance of the proposed AMA has been studied on a real-time multirobot path-planning problem. Experimental results obtained for both simulation and real frameworks indicate that the proposed algorithm-based path-planning scheme outperforms the real-coded genetic algorithm, particle swarm optimization, and DE, particularly its currently best version with respect two standard metrics defined in the literature.

Memetic algorithms are population-based meta-heuristic search algorithms that combine the composite benefits of natural and cultural evolution. In this paper a synergism of the classical Differential Evolution algorithm and Q-learning is used to construct the memetic algorithm. Computer simulation with standard benchmark functions reveals that the proposed memetic algorithm outperforms three distinct Differential Evolution algorithms.

The paper presents an elegant approach for designing linear phase low pass digital FIR filter using swarm and evolutionary algorithms. Classical gradient based approaches are not efficient enough for accurate design and thus evolutionary approach is considered to be a better choice. In this paper a hybrid of Genetic Algorithm and Particle Swarm Optimization algorithm with varying neighbourhood topology, namely Genetic Lbest Particle Swarm Optimization with Dynamically Varying Neighbourhood (GLPSO DVN) is used to find the filter coefficients. In this work two objective functions (error metrics) are minimized. The first one is based on stop and pass band ripple and the second one studies the mean square error between the ideal and actual designed filter. The hybrid algorithm is found to produce fitter candidate solution than the classical Lbest PSO. The results are compared with the results obtained by solving the same problem using Lbest PSO (LPSO). It is also observed that GLPSO DVN gives better results than LPSO and as well LPSO DVN.

This paper provides a new approach to include the chemotactic behavior of Bacterial Foraging Algorithm (BFOA) in the existing Improved Harmony Search (IHS) algorithm. Extensive computer simulations with CEC-2005 benchmark functions reveal that the proposed algorithm outperforms the existing one with respect to accuracy in determining the optima. The proposed algorithm has successfully been implemented for multi-robot motion planning application. Performance has been studied using the proposed IHS-BFO algorithm and compared with existing IHS and Particle Swarm Optimization (PSO) algorithm.

In recent years there has been a growing trend in the application of Memetic Algorithms for solving numerical optimization problems. They are population based search heuristics that integrate the benefits of natural and cultural evolution. In this paper, we propose an Adaptive Memetic Algorithm, named LA-DE which employs a competitive variant of Differential Evolution for global search and Learning Automata as the local search technique. During evolution Stochastic Automata Learning helps to balance the exploration and exploitation capabilities of DE resulting in local refinement. The proposed algorithm has been evaluated on a test-suite of 25 benchmark functions provided by CEC 2005 special session on real parameter optimization. Experimental results indicate that LA-DE outperforms several existing DE variants in terms of solution quality.

The essence of the paper is to reduce uncertainty in interval type-2 fuzzy sets, and demonstrate the merit of uncertainty reduction in pattern classification problem. The area under the footprint of uncertainty has been used as the measure of uncertainty. A mathematical approach to reduce the area under the footprint of uncertainty has been proposed. Experiments have been designed to compare the relative performance of the classical interval type-2 fuzzy sets with its revised counterpart in emotion recognition from facial expression. Statistical tests performed favor the proposed results of uncertainty reduction. The proposed uncertainty reduction scheme helps in saving approximately 6% gain in classification accuracy with respect to one published work when applied to emotion recognition problem.

The sense of touch is an extremely important sensory system in the human body which helps to understand object shape, texture, hardness in the world around us. Incorporating artificial haptic sensory systems in rehabilitative aids and in various other human computer interfaces is a thrust area of research presently. This paper presents a novel approach of shape recognition and classification from the tactile pressure images by touching the surface of various real life objects. Here four objects (viz. a planar surface, object with one edge, a cuboid i.e. object with two edges and a cylindrical object) are used for shape recognition. The obtained tactile pressure images of the object surfaces are subjected to segmentation, edge detection and a mapping procedure to finally reconstruct the particular object shapes. The reconstructed images are used as features. The processed tactile pressure images are classified with feed- forward neural network (FFNN) using extracted features. The classifier performance is tested with different signal-to-noise (SNR) ratios. Is is observed that classifier accuracy decreases with decrease in SNR, but at SNR value 6 i.e. when the noise power is one sixth of the signal power, the mean classification accuracy of the classifier is 88%. This shows the robustness of feed-forward neural network in the classification purpose. The performance of FFNN is compared with four classifiers (Linear Discriminant Analysis, Linear Support vector machine, Radial Basis Function SVM, k-Nearest Neighbor). FFNN performed best acquiring first rank with a average classification accuracy of 94.0%.

Wireless Mesh Networks (WMNs) have drawn much attention for emerging as a promising technology to meet the challenges in next generation networks. Security and privacy protection have been the primary concerns in pushing the success of WMNs. However, the solutions proposed to ensure the security of the routing protocol and the privacy information in WMNs are still not robust. In this paper, we propose a role based privacy-aware secure routing protocol (RPASRP), which combines a new dynamic reputation mechanism with the role based multi-level security technology and a novel hierarchical key management protocol to defend against the internal attacks and to achieve better security and privacy protection. Simulation results show that RPASRP implements the security and privacy protection against the inside attacks more effectively and efficiently and performs better than the classical hybrid wireless mesh protocol (HWMP) in terms of packet delivery ratio.

One of the major concerns of research in integrated healthcare information systems is to enable decision support among clinicians across boundaries of organizations and regional workgroups. A necessary precursor, however, is to facilitate the construction of appropriate awareness of local clinical practices, including a clinician's actual cognitive capabilities, peculiar workplace circumstances, and specific patient-centered needs based on real-world clinical contexts across work settings. In this paper, a user-centered study aimed to investigate clinical practices across three different geographical areas-the U.K., the UAE and Nigeria-is presented. The findings indicate that differences in clinical practices among clinicians are associated with differences in local work contexts across work settings, but are moderated by adherence to best practice guidelines and the need for patient-centered care. The study further reveals that an awareness especially of the ontological, stereotypical, and situated practices plays a crucial role in adapting knowledge for cross-boundary decision support. The paper then outlines a set of design guidelines for the development of enterprise information systems for e-health. Based on the guidelines, the paper proposes the conceptual design of CaDHealth, a practice-centered framework for making sense of clinical practices across work settings for effective cross-boundary e-health decision support.

This paper presents the design of Cad Health, a system aimed at enabling knowledge and work practice transfer among clinicians across geographical, regional and workplace boundaries for effective clinical decision support in e-health. The system offers a unifying structure that allows clinicians to make sense of clinical work situations across regional and workplace boundaries in an e-health environment. The approach we have taken in Cad Health is motivated by the fact that 1) patterns of clinical work practice have been found to vary significantly across work settings, and 2) the contextual cues and practice-based knowledge, which are offered by common problem solving contexts in co-located work settings, and which enable clinicians, in such settings, to share information and knowledge to support one another's clinical decision making do not exist in e-health and other distributed work contexts. In particular, we highlight a number of user-informed design considerations, and describe the architecture and prototype of Cad Health.

Throughout history people have created designs and patterns to express their cultural beliefs. Most of these art patterns, such as the Sona art form, have been shown to incorporate interesting mathematical concepts, and a number of computer-based models of the Sona art form have been developed. However, efforts are still lacking towards building Sona art form models for the mobile platform. This paper presents the design of a mobile-based platform of Sona art form, and shows how the hidden geometrical principles in the traditional design can be used to form new patterns. An algorithmic procedure for testing a form of the Sona design as well as a case study focusing on mobile learning is described.

Manifestation of a given emotion on facial expression is not always unique, as the facial attributes in different instances of similar emotional experiences may vary widely. When a number of facial attributes are used to recognize the emotion of a subject, the variation of individual attributes together makes the problem more complicated. This variation is the main source of uncertainty in the emotion recognition problem, which has been addressed here in two steps using type-2 fuzzy sets. First a type-2 fuzzy face-space is constructed with the background knowledge of facial features of different subjects for different emotions. Second, the emotion of the unknown subject is determined based on the consensus of the measured facial features with the fuzzy face-space. The face-space comprises both primary and secondary membership distributions. The primary membership distributions here have been constructed based on the highest frequency of occurrence of the individual attributes. Naturally, the membership values of an attribute at all except the point of highest frequency of occurrence suffer from inaccuracy, which has been taken care of by secondary memberships. An algorithm for the evaluation of the secondary membership distribution from its type-2 primary counterpart has been proposed. The uncertainty management policy adopted using general type-2 fuzzy set has a classification accuracy of 96.67% in comparison to 88.67 % obtained by interval type-2 counterpart only.

Disabled people now expect better quality of life with the development of brain computer interfaces (BCIs) and neuroprosthetics. EEG (electroencephalograph) based BCI research for robot arm control mainly concentrates on distinguishing the left/right arm movement. But for controlling artificial arm in real life scenario with greater degrees of freedom, it is essential to classify the left/right arm movement further into different joint movements. In this paper we have classified the raw EEG signal for left and right hand movement, followed by further classification of each hand movement into elbow, finger and shoulder movements. From the two electrodes of interest, namely, C3 and C4, wavelet coefficients, power spectral density (PSD) estimates for the alpha and beta bands and their corresponding powers were selected as the features for this study. These features are further fed into the quadratic discriminant analysis (QDA), linear support vector machine (LSVM) and radial basis function kernelized support vector machine (RSVM) to classify into the intended classes. For left-right hand movement, the maximum classification accuracy of 87.50% is obtained using wavelet coefficient for RSVM classifier. For the multi-class classification, i.e., Finger-Elbow-Shoulder classification the maximum classification accuracy of 80.11% for elbow, 93.26% for finger and 81.12% for shoulder is obtained using the features obtained from power spectral density for RSVM classifier. The results presented in this paper indicates that elbow-finger-shoulder movement can be successfully classified using the given set of features.

This study concerns the problem of controlling multiclass (elastic, inelastic and unresponsive) Internet traffic without sacrificing quality of service (QoS) by adopting a unified ‘resource allocation and traffic management’ approach. The aim is to minimise the need for relying on dedicated QoS traffic control mechanisms in order to avoid spiralling complicatedness that, in practice, leads to ‘robust yet fragile’ Internet. In order to address this challenge, the authors first introduce an end-to-end non-convex network utility maximisation-based resource allocation algorithm to guarantee enhanced QoS to elastic and inelastic flows. Then, a pricing-based fair and scalable traffic management scheme, called Purge, is introduced to protect transmission control protocol-friendly traffic from unfairness attacks by unresponsive flows. Finally, the main contribution of this work, the unified algorithm, is developed by adapting Purge to complement link-control of the proposed resource allocation algorithm to enable it to enforce fairness while maintaining a scalable network core. The unified approach thus delivers QoS guarantees for multiclass traffic.

The paper employs Lagrange's mean value theorem of differential Calculus to design a new strategy for the selection of parameter vectors in the Differential Evolution (DE) algorithm. Classical differential evolution selects parameter vectors randomly to obtain the donor vectors. These donor vectors thus cannot be directly used as trial solution to the optimization problem. The recombination step indeed is very useful to generate potential trial solutions. The proposed algorithm eliminates the recombination step as the trial solutions can be directly generated by the extended mutation step only. Performance analysis of the proposed algorithm with respect to standard benchmark functions reveals that both in expected convergence time and accuracy in solutions, the proposed algorithm outperforms classical DE/rand/1. Besides extension in mutation strategy, an adaptive selection strategy in the scaling factor F also improves the performance of the proposed algorithm. In addition, the proposed algorithm outperforms classical DE in noisy optimization problem. Further, the number of function evaluation with scaled up dimensions of the optimization problem adds insignificantly small complexity in comparison to that in classical differential evolution to meet up a prescribed level of accuracy in solution quality.

The paper proposes a new approach to fuzzy abduction by extending the contraposition rule of propositional logic. The main difficulty of fuzzy abduction is due to the restriction of single antecedent clause in a fuzzy production rule. When more than one antecedent clause occurs jointly in a fuzzy rule, the membership value of the derived antecedent clauses become equal, which should not be the case in general. The paper overcomes this problem and demonstrates a simple but elegant method to compute premises in a multi-chained reasoning system.

Gene regulatory network provides the knowledge of interaction strength among the genes in living organisms. Accurate identification of gene regulatory network is of prime interest to the researchers in recent time. Different researchers applied different optimization techniques to solve this problem. Most of these optimization techniques considers the square error between reference and simulated gene expression as their objective and minimize it to get a solution for the identification problem under consideration. But these techniques do not guarantee a unique set of network parameter, because the squared error is a non-linear multimodal surface of network parameters. Therefore considering only square error as the objective function is not a good choice. An alternative way of formulation of this problem is to validate it from different perspective. In this paper, we propose a technique for identification of gene regulatory network using multiple objectives. The objectives are designed to make the identification technique more robust. Multi-objective differential evolution is used to find a set of pareto-optimal solutions with respect to the objective functions. Among those solutions, one is chosen according to some suitable criterion. Computer simulation has shown that the proposed technique can identify useful interaction information from gene expression time series data.

In the context of e-health, professionals and healthcare service providers in various organisational and geographical locations are to work together, using information and communication systems, for the purpose of providing better patient-centred and technology-supported healthcare services at anytime and from anywhere. However, various organisations and geographies have varying contexts of work, which are dependent on their local work culture, available expertise, available technologies, people's perspectives and attitudes and organisational and regional agendas. As a result, there is the need to ensure that a suggestion - information and knowledge - provided by a professional to support decision making in a different, and often distant, organisation and geography takes into cognizance the context of the local work setting in which the suggestion is to be used. To meet this challenge, we propose a framework for context-aware knowledge modelling in e-health, which we refer to as ContextMorph. ContextMorph combines the commonKADS knowledge modelling methodology with the concept of activity landscape and context-aware modelling techniques in order to morph, i.e. enrich and optimise, a knowledge resource to support decision making across various contexts of work. The goal is to integrate explicit information and tacit expert experiences across various work domains into a knowledge resource adequate for supporting the operational context of the work setting in which it is to be used.

The paper proposes a novel formulation of the classical box-pushing problem by mobile robots as a multi-objective optimization problem, and presents Pareto optimal solution to the problem using non-dominated sorting genetic algorithm-II (NSGA-II). The proposed method adopts local planning scheme, and allows both turning and translation of the box in the robots' workspace in order to minimize the consumption of both energy and time. The planning scheme introduced here determines the magnitude of the forces applied by two mobile robots at specific location on the box in order to align and translate it along the time- and energy- optimal trajectory in each distinct step of motion of the box. The merit of the proposed work lies in autonomous selection of translation distance and other important parameters of the robot motion model using NSGA-II. The suggested scheme, to the best of the authors' knowledge, is a first successful realization of a communication-free, centralized cooperation between two robots used in box shifting problem satisfying both time and energy minimization objectives simultaneously, presuming no additional user-defined constraint on the selection of linear distance traversal.

A gene regulatory network describes the influence of genes over others. This paper attempts to model gene regulatory network by a recurrent neural net with fuzzy membership distribution of weights. A cost function is designed to match the response of neurons in the network with the gene expression data, and a differential evolution algorithm is used to minimize the cost function. The minimization yields fuzzy membership distribution of weights, which on de-fuzzification provides the desired signed weights of the gene regulatory network. Computer simulation reveals that the proposed method outperforms existing techniques in detecting sign, and magnitude of weights of the regulatory network.

In fuzzy abduction, one needs to evaluate the membership distribution of the premise (antecedent clause), when the membership distribution of the consequent clause, and the fuzzy implication relations between the antecedent and the consequent clauses are provided. The paper formulates and solves the problem of fuzzy abduction by using type-2 fuzzy sets. It presumes background knowledge about the primary and the secondary antecedent to consequent implication relations to uniquely determine the type-2 fuzzy set corresponding to the antecedent clause, when the same for the consequent clause is provided. The proposed methodology of abduction would serve many interesting applications on predictions, forecasting, and diagnosis, where the environmental factor can be modeled with type-2 secondary distributions.

Network utility maximization (NUM) provides an important perspective to conduct rate allocation where optimal performance, in terms of maximal aggregate bandwidth utility, is generally achieved such that each source adaptively adjusts its transmission rate. Behind most of the recent literature on NUM, common assumptions are that traffic flows are elastic and that their utility functions are strictly concave. This provides design simplicity but, in practice, limits the applicability of resulting protocols, in that severe QoS problems may be encountered when bandwidth is shared by inelastic flows. This paper investigates the problem of distributively allocating data transmission rates to multiclass services, both elastic and inelastic, and overcomes the restrictive and often unrealistic assumptions. The proposed method is based on the Lagrangian Relaxation for a dual formulation that decomposes the higher dimension NUM into a number of subproblems. We use a novel Surrogate Subgradient based stochastic method to solve the dual problem. Unlike the ordinary subgradient methods, surrogate subgradient can compute optimal prices without the need to solve all the subproblems. For the lower dimension, nonlinear and nonconvex subproblems we use a hybrid particle swarm optimization (PSO) and sequential quadratic programming (SQP) method, where the objective is to achieve fast convergence as well as accuracy. We demonstrate the efficiency of the proposed rate allocation algorithm, in terms maintaining QoS for multiclass services, and validate its scalability and accuracy for large scale flows.

Determining correlation between aroused emotion and its manifestation on facial expression, voice, gesture and posture have interesting applications in psychotherapy. A set of audiovisual stimulus, selected by a group of experts, is used to excite emotion of the subjects. EEG and facial expression of the subjects excited by the selected audio-visual stimulus are collected, and the nonlinear-correlation from EEG to facial expression, and vice-versa is obtained by employing feed-forward neural network trained with back-propagation algorithm. Experiments undertaken reveals that the trained network can reproduce the correlated EEG-facial expression trained instances with 100 % accuracy, and is also able to predict facial expression (EEG) from unknown EEG (facial expression) of the same subject with an accuracy of around 95.2%.

The two areas of grammar systems and P systems, which have provided interesting computational models in the study of formal string language theory have been in the recent past effectively linked in [4] by incorporating into P systems, a communication mode called t–mode of cooperating distributed grammar systems. On the other hand cooperating array grammar systems [5] and array P systems [1] have been developed in the context of two-dimensional picture description. In this paper, motivated by the study of [4], these two systems are studied by linking them through the t–communication mode, thus bringing out the picture description power of these systems.