The convergence property for doing logic programming in Hopfield network can be accelerated by using new relaxation method. This paper shows that the performance of the Hopfield network can be improved by using a relaxation rate to control the energy relaxation process. The capacity and performance of these networks is tested by using computer simulations. It was proven by computer simulations that the new approach provides good solutions.
Adaptive Neuro Fuzzy Inference System (ANFIS) is among the most efficient classification and prediction
modelling techniques used to develop accurate relationship between input and output parameters in
different processes. This paper reports the design and evaluation of the classification performances of
two discrete Adaptive Neuro Fuzzy Inference System models, ANFIS Matlab’s built-in model (ANFIS_
LSGD) and a newly ANFIS model with Levenberg-Marquardt algorithm (ANFIS_LSLM). Major steps
were performed, which included classification using grid partitioning method, the ANFIS trained with
least square estimates and backpropagation gradient descent method, as well as the ANFIS trained with
Levenberg-Marquardt algorithm using finite difference technique for computation of a Jacobian matrix.
The proposed ANFIS_LSLM model predicts the degree of patient’s heart disease with better, reliable
and more accurate results. This is due to its new feature of index membership function that determines
the unique membership functions in an ANFIS structure, which indexes them into a row-wise vector. In
addition, an attempt was also done to specify the effectiveness of the model’s performance measuring
accuracy, sensitivity and specificity. A comparison of the two models in terms of training and testing
with the Statlog-Cleveland Heart Disease dataset have also been done.
Medical diagnosis is the process of determining which disease or medical condition explains a person’s determinable signs and symptoms. Diagnosis of most diseases is very expensive as many tests are required for predictions. This paper aims to introduce an improved hybrid approach for training the adaptive network based fuzzy inference system (ANFIS). It incorporates hybrid learning algorithms least square estimates with Levenberg-Marquardt algorithm using analytic derivation for computation of Jacobian matrix, as well as code optimisation technique, which indexes membership functions. The goal is to investigate how certain diseases are affected by patient’s characteristics and measurement such as abnormalities or a decision about the presence or absence of a disease. In order to achieve an accurate diagnosis at this complex stage of symptom analysis, the physician may need efficient diagnosis system to classify and predict patient condition by using an adaptive neuro fuzzy inference system (ANFIS) pre-processed by grid partitioning. The proposed hybridised intelligent technique was tested with Statlog heart disease and Hepatitis disease datasets obtained from the University of California at Irvine’s (UCI) machine learning repository. The robustness of the performance measuring total accuracy, sensitivity and specificity was examined. In comparison, the proposed method was found to achieve superior
performance when compared to some other related existing methods.
Maximum k-Satisfiability (MAX-kSAT) consists of the most consistent interpretation that generate the maximum number
of satisfied clauses. MAX-kSAT is an important logic representation in logic programming since not all combinatorial
problem is satisfiable in nature. This paper presents Hopfield Neural Network based on MAX-kSAT logical rule. Learning
of Hopfield Neural Network will be integrated with Wan Abdullah method and Sathasivam relaxation method to obtain
the correct final state of the neurons. The computer simulation shows that MAX-kSAT can be embedded optimally in
Hopfield Neural Network.
In this study, a hybrid approach that employs Hopfield neural network and a genetic algorithm in
doing k-SAT problems was proposed. The Hopfield neural network was used to minimise logical
inconsistency in interpreting logic clauses or programme. Hybrid optimisation made use of the global
convergence advantage of the genetic algorithm to deal with learning complexity in the Hopfield
network. The simulation incorporated with genetic algorithm and exhaustive search method with different
k-Satisfiability (k-SAT) problems, namely, the Horn-Satisfiability (HORN-SAT), 2-Satisfiability (2-SAT)
and 3-Satisfiability (3-SAT) will be developed by using Microsoft Visual C++ 2010 Express Software.
The performance of both searching techniques was evaluated based on global minima ratio, hamming
distance and computation time. Simulated results suggested that the genetic algorithm outperformed
exhaustive search in doing k-SAT logic programming in the Hopfield network.
Swarm intelligence is a research area that models the population of swarm that is able to self-organise effectively. Honey bees that gather around their hive with a distinctive behaviour is another example of swarm intelligence. In fact, the artificial bee colony (ABC) algorithm is a swarm-based meta-heuristic algorithm introduced by Karaboga in order to optimise numerical problems. 2SAT can be treated as a constrained optimisation problem which represents any problem by using clauses containing 2 literals each. Most of the current researchers represent their problem by using 2SAT. Meanwhile, the Hopfield neural network incorporated with the ABC has been utilised to perform randomised 2SAT. Hence, the aim of this study is to investigate the performance of the solutions produced by HNN2SAT-ABC and compared it with the traditional HNN2SAT-ES. The comparison of both algorithms has been examined by using Microsoft Visual Studio 2013 C++ Express Software. The detailed comparison on the performance of the ABC and ES in performing 2SAT is discussed based on global minima ratio, hamming distance, CPU time and fitness landscape. The results obtained from the computer simulation depict the beneficial features of ABC compared to ES. Moreover, the findings have led to a significant implication on the choice of determining an alternative method to perform 2SAT.
Artificial neural networks (ANNs) are actively utilized by researchers due to their extensive capability during the training process of the networks. The intricate training stages of many ANNs provide a powerful mechanism in solving various optimization or classification tasks. The integration of an ANN with a robust training algorithm is the supreme model to outperform the existing framework. Therefore, this work presented the inclusion of three satisfiability Boolean logic in the Hopfield neural network (HNN) with a sturdy evolutionary algorithm inspired by the Imperialist Competitive Algorithm (ICA). In general, ICA stands out from other metaheuristics as it is inspired by the policy of extending the power and rule of a government/country beyond its own borders. Existing models that incorporate standalone HNN are projected as non-versatile frameworks as it fundamentally employs random search in its training stage. The main purpose of this work was to conduct a comprehensive comparison of the proposed model by using two real data sets with an elementary HNN with exhaustive search (ES) versus a HNN with a standard evolutionary algorithm, namely- the genetic algorithm (GA). The performance evaluation of the proposed model was analyzed by computing plausible errors, such as root mean square error (RMSE), mean absolute error (MAE), global minima ratio (Rm), computational time (CT) and accuracy (Q). The computational simulations were carried out by operating the different numbers of neurons in order to validate the efficiency of the proposed model in the training stage. Based on the simulations,
the proposed model was found to execute the best performance in terms of attaining small
errors and efficient computational time compared to other existing models.
Analyzing commodity prices contributes greatly to traders, economists and analysts in
ascertaining the most feasible investment strategies. Limited knowledge about the price
trend of the commodities indeed will affect the economy because commodities like palm
oil and gold contribute a huge source of income to Malaysia. Therefore, it is important to
know the optimal price trend of the commodities before making any investments. Hence,
this paper presents a logic mining technique to study the price trend of palm oil with other
commodities. This technique employs 2-Satisfiability based Reverse Analysis Method
(2-SATRA) consolidated with 2-Satisfiability logic in Discrete Hopfield Neural Network
(DHNN2-SAT). All attributes in the data set are represented as a neuron in DHNN which
will be programmed based on a 2-SAT logical rule. By utilizing 2-SATRA in DHNN2-SAT,
the induced logic is generated from the commodity price data set that explains the trend
of commodities price. Following that, the performance evaluation metric; error analysis
and accuracy will be calculated based on the induced logic. In this case, the experimental
result has shown that the best-induced logic identifies which trend will lead to an increase
in the palm oil price with the highest accuracy rate.