Search

In the existing network-layered architectural stack of Cognitive Radio Ad Hoc Network (CRAHN), channel selection is performed at the Medium Access Control (MAC) layer. However, routing is done on the network layer. Due to this limitation, the Secondary/Unlicensed Users (SUs) need to access the channel information from the MAC layer whenever the channel switching event occurred during the data transmission. This issue delayed the channel selection process during the immediate routing decision for the channel switching event to continue the transmission. In this paper, a protocol is proposed to implement the channel selection decisions at the network layer during the routing process. The decision is based on past and expected future routing decisions of Primary Users (PUs). A learning agent operating in the cross-layer mode of the network-layered architectural stack is implemented in the spectrum mobility manager to pass the channel information to the network layer. This information is originated at the MAC layer. The channel selection is performed on the basis of reinforcement learning algorithms such as No-External Regret Learning, Q-Learning, and Learning Automata. This leads to minimizing the channel switching events and user interferences in the Reinforcement Learning- (RL-) based routing protocol. Simulations are conducted using Cognitive Radio Cognitive Network simulator based on Network Simulator (NS-2). The simulation results showed that the proposed routing protocol performed better than all the other comparative routing protocols in terms of number of channel switching events, average data rate, packet collision, packet loss, and end-to-end delay. The proposed routing protocol implies the improved Quality of Service (QoS) of the delay sensitive and real-time networks such as Cellular and Tele Vision (TV) networks.

Fuzzy logic is an algorithm that works on “degree of truth”, instead of the conventional crisp logic where the possible answer can be 1 or 0. Fuzzy logic resembles human thinking as it considers all the possible outcomes between 1 and 0 and it tries to reflect reality. Generation of membership functions is the key factor of fuzzy logic. An approach for generating fuzzy gaussian and triangular membership function using fuzzy c-means is considered in this research. The problem related to sunspot prediction is considered and its accuracy is calculated. It is evident from the results that the proposed technique of generating membership functions using fuzzy c-means can be adopted for predicting sunspots.

Techniques involved artificial intelligence and machine learning offers various classification methods in order to deal with daily life problems. Among these methods, Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Deep Neural Network (DNN) are the most commonly used classifiers. Since ANFIS is not suitable for high-dimensional data, therefore DNN was introduced to overcome this problem faced by conventional methods. However, due to the optimization of millions of parameters in their deep architecture, the decision made by DNN faced the criticism of being non-transparent. To overcome this problem, recently, various researchers are coming up with the idea of using fuzzy logic with DNN. Therefore, this study also proposed a Deep Neuro-Fuzzy Classifier (DNFC) with a cooperative based structure for solving classification problems, particularly. The performance of the proposed DNFC was evaluated with ANFIS and DNN classifier, where overall results show that the performance of ANFIS classifier decreased when input size increased. While the performance of the proposed model demonstrated nearly similar or slightly higher accuracy as compared to DNN.

Fuzzy logic is a way of many-valued computing logic that deals with the truth values of the variables between 0 and 1, unlike the conventional Boolean logic. Membership functions are used to depict the fuzzy values of given variable. Though membership functions are determined through expert’s opinion, however, the one estimated through heuristic algorithms is the preferable methods. Membership functions determined through statistical and knowledge engineering methods are usually application dependent and cannot be applied on different datasets. This research focuses on generating the parametric values of the triangular membership function using a novel method. Initially, the Fuzzy C-means algorithm is utilized to generate the parameters values of the Gaussian membership function. Using a set of equations, these values then estimate the parameters of the triangular membership function. The proposed method is applied to the quality of web services data. From the results it is verified that the new approach of generating triangular membership functions can be adopted.

Data-driven predictive maintenance for the prediction of machine failure has been widely studied and performed to test machine failures. Predictive maintenance refers to the machine learning method, which utilizes data for identification of potential system malfunction and provides an alert when a system assessed to be prone to breakdown. The proposed work reveals a novel framework called Artificial Intelligence Monitoring 4.0 (AIM 4.0), which is capable of determining the current condition of equipment and provide a predicted mean time before failure occurs. AIM 4.0 utilizes three different ensemble machine learning methods, including Gradient Boost Machine (GBM), Light GBM, and XGBoost for prediction of machine failures. The machine learning methods stated are implemented to produce acceptable accuracy for the monitoring task as well as producing a prediction with a high confidence level.

Sea has always played a pivotal role in human life. It formulates the weather, provides transportation medium, food, natural resources like oil and gas, and much more. Countless commercial and industrial activities take place on the surface of the sea, thus understanding, classifying and predicting the sea surface wave is a topic of great interest. Many numerical models (NM) have been proposed to model the behavior of sea waves, however, they are complex and costly for site-specific studies. On the other hand, data-driven machine learning (ML) models have recently proved to be an effective solution for site-specific classification, real-time or near-future prediction problems. The ML approach utilizes marine datasets to train, test and validate the model. In this paper, we present a survey of ML studies on the topic of classification and prediction of sea wave parameters. We hope that this paper provides a holistic model-based view to new researchers and pave the path for future research.

This paper proposes a hybrid prediction technique based on Recurrent Neural Network Long-Short-Term Memory (RNN-LSTM) with the integration of Particle Swarm Optimization (PSO) algorithm to estimate the Remaining Useful Life (RUL) of machines. LSTM is an improvement of RNN as RNN faces issues with predicting long-term dependencies. Issues such as vanishing and exploding gradients are the results of backpropagating errors, taking place when the network is learning to store and relate information over extended time intervals. RNN-LSTM is a feasible technique for this research due to its effectiveness in resolving sequential long-term dependencies problems. However, the accuracy can still be enhanced to a satisfactory value considering the optimal network topology has not been discovered yet. Accuracy improvement can be achieved by resorting to hyperparameter tuning. A result of proof of concept validates that by increasing the number of epochs, the accuracy of prediction has improved but increases the execution time. To optimize between the accuracy and execution time, a population-inspired Particle Swarm Optimization (PSO) algorithm is employed. PSO will be utilized to select the optimal RNN-LSTM topology specifically the learning rate instead of using manual search. This optimized hybrid prediction technique is useful to be implemented in predictive maintenance to predict machine failure.

Clustering is more popular than the expert knowledge approach in Interval Fuzzy Type-2 membership function construction because it can construct membership function automatically with less time consumption. Most research proposed a two-fuzzifier fuzzy C-Means clustering method to construct Interval Fuzzy Type-2 membership function which mainly focused on producing Gaussian membership function. The other two important membership functions, triangular and trapezoidal, are constructed using the grid partitioning method. However, the method suffers a drawback of not being able to represent actual data composition in the underlying dataset. Some research proposed triangular and trapezoidal membership functions construction using readily formed Fuzzy Type-1 membership functions, which means it remains unclear how the membership functions are heuristically constructed using fuzzy C-Means outputs. The triangular and trapezoidal membership functions are important because previous works have shown that they may produce superior performance than Gaussian membership function in some applications. Therefore, this paper presents a structured literature review on generating triangular and trapezoidal Interval Fuzzy Type-2 membership functions using fuzzy C-Means. Initially, 110 related manuscripts were collected from Web of Science, Scopus, and Google Scholar. These manuscripts went through the identification, screening, eligibility, and inclusion processes, and as a result, 21 manuscripts were reviewed and discussed in this paper. To ensure that the review also covers the important components of fuzzy logic, this paper also reviews and discusses another 49 manuscripts on fuzzy calculation and operation. Furthermore, this paper also discusses the contributions of the conducted review to the body of knowledge, future research directions and challenges, with the aim to motivate the future works of constructing the methods to generate Interval Fuzzy Type-2 triangular and trapezoidal membership functions using fuzzy C-Means. The methods imply flexibility in choosing membership function type, hence increasing the effectiveness of fuzzy applications through leveraging the advantages that each of the three membership function types could provide.

Data Streams create new challenges for fuzzy clustering algorithms, specifically Interval Type-2 Fuzzy C-Means (IT2FCM). One problem associated with IT2FCM is that it tends to be sensitive to initialization conditions and therefore, fails to return global optima. This problem has been addressed by optimizing IT2FCM using Ant Colony Optimization approach. However, IT2FCM-ACO obtain clusters for the whole dataset which is not suitable for clustering large streaming datasets that may be coming continuously and evolves with time. Thus, the clusters generated will also evolve with time. Additionally, the incoming data may not be available in memory all at once because of its size. Therefore, to encounter the challenges of a large data stream environment we propose improvising IT2FCM-ACO to generate clusters incrementally. The proposed algorithm produces clusters by determining appropriate cluster centers on a certain percentage of available datasets and then the obtained cluster centroids are combined with new incoming data points to generate another set of cluster centers. The process continues until all the data are scanned. The previous data points are released from memory which reduces time and space complexity. Thus, the proposed incremental method produces data partitions comparable to IT2FCM-ACO. The performance of the proposed method is evaluated on large real-life datasets. The results obtained from several fuzzy cluster validity index measures show the enhanced performance of the proposed method over other clustering algorithms. The proposed algorithm also improves upon the run time and produces excellent speed-ups for all datasets.

Inappropriate team composition is one of the important factors that can impact the overall process of software development. Numerous models for team composition have also been suggested, yet they have been disapproved by the researchers and organisations for having ineffectiveness in yielding positive results. Therefore, this study proposes a rough-fuzzy model for selecting team leader for software development teams to avoid the limitations of individual techniques (i.e., Rough Set Theory (RST) or Fuzzy Set Theory (FST)). Moreover, the model development was divided into two portions: Decision Rules Development and Fuzzy Inference System (FIS) development. Johnson Algorithm (JA) was applied using ROSETTA toolkit under rough set theory principles for decision rule construction. Decision rules were then used under Mamdani’s fuzzy inference method. At the end, the developed model was validated based on the results of prediction accuracy and F1-measures.

There are existing implementations of Latent Dirichlet Allocation (LDA) algorithm as a semantic classifier to arrange the data for efficient retrieval. However, the problem of learning or inferencing the posterior distribution of the algorithm is trivial. Inferencing directly the prior distribution could lead to time taken to increase exponentially. It is due to the coupling of the hyperparameters. Several inference algorithms have been implemented together with LDA to solve this issue. The inference algorithm used in this research work is Gibbs sampling. Research using Gibbs sampling shows promising results in comparison to other inference algorithms, especially in the performance of the algorithm. It still takes a long time to compute the topic distribution of the data. There are still room for improvement in the time taken for the algorithm to complete the topic distribution. Using two datasets, an evaluation of the performance of the algorithm has been conducted. Results show that Gibbs sampling as the inference algorithm provides a better prediction on the optimal number of topic of the data in comparison to Variational Expectation Maximization (VEM).

This paper presents a comparative study of fuzzy inference system (FIS) with respect to Mamdani and Sugeno FISs to show the accuracy and precision of quality of web service (QoWS) compliance monitoring. We used these two types of FIS for designing the QoWS compliance monitoring model. Clustering validity index is used to optimize the number of clusters of both models. Then both models are constructed based on Fuzzy CMeans (FCM) clustering algorithm. Simulation results with a Mamdani model, a Sugeno model and a crisp-based model for benchmark are presented. We consider different levels of noise (to represent uncertainties) in the simulations for comparison and to analyze the performance of the models when applied in QoWS compliance monitoring. The results show that Sugeno FIS outperforms Mamdani FIS in terms of accuracy and precision by producing better total error, error percentage, precision, mean squared error and root mean squared error measurements.The advantage of using fuzzy-based model is also verified with benchmark model.

Programming is a cognitive activity which requires logical reasoning to code for abstract presentation. This study aims to find out the personality traits of students who maintain the effective grades in learning programming courses such as structured programming (SP) and object oriented programming (OOP) by gender classification. Data were collected from three universities to develop, validate, and generalize the Rough-Fuzzy model. Genetic and Johnson algorithms were applied under Rough set theory’s (RST) principles to extract the decision rules. In addition, Standard Voting, Naive Bayesian, and Object Tracking procedures were applied on the generated decision rules to find the prediction accuracy of each algorithm. Mamdani’s Fuzzy Inference System (FIS) was used for mapping the decision rules’ condition (input) to decision (output) based on fuzzy set theory (FST) to develop the model. The results highlighted that certain personality compositions can be suitable for scoring good grades in programming subjects. For instance, a female student is capable enough to improve the programming skills if she is composed of introvert and sensing personality traits. Therefore, it is important to investigate an appropriate personality composition for programming learners.

Existing works investigated the construction of fuzzy type-1 (FT1) membership function (MF). However, recent findings show that interval type-2 (IT2)-based fuzzy inference system (FIS) is found to be more accurate and precise than FT1. Hence, the research on how to generate IT2 MF from data is significant to be conducted. Besides, existing works also investigated the construction of IT2 MF using IT2 Fuzzy C-Means (FCM) method. The evident shows that the construction of IT2 MF from IT2 FCM method may not suitable for all kind of data sets. Hence, the objectives of this paper are to present a methodology for the generation of IT2 MF using general FCM (non-IT2 FCM) data clustering method and to describe the implementation of the proposed IT2 MFs in an FIS. The experiment results show that IT2 MFs have successfully been constructed by using general FCM and two clusters' centers approach.