International Journal of Computational Intelligence Studies (19 papers in press)
Combining Multi-objective evolutionary algorithm with averaged one-dependence estimators for Big Data Analytics
by Mrutyunjaya Panda
Abstract: Even though many researchers tried to explore the various possibilities on multi-objective feature selection, still, it is yet to be explored with best of its capabilities in data mining applications rather than going for developing new ones. In this paper, multi-objective evolutionary algorithm ENORA is used to select the features in a multi-class classification problem. The fusion of AnDE (averaged n-dependence estimators) with n=1, a variant of naive Bayes with efficient feature selection by ENORA is performed in order to obtain a fast hybrid classifier which can effectively learn from big data. This method aims at solving the problem of finding optimal feature subset from full data which at present still remains to be a difficult problem. The efficacy of the obtained classifier is extensively evaluated with a range of most popular 21 real world dataset, ranging from small to big ones. The results obtained are encouraging in terms of time; Root means square error; zero-one loss and classification accuracy.
Keywords: MOEA; ENORA; AODE; Classification; 0/1 loss; RMSE; t-test.
Design of a parity preserving reversible full adder/subtractor circuit
by Mohammad Reza Reshadinezhad, Shiva Rahbar Arabani
Abstract: The reversible logical circuits, due to their economized power consumption in comparison with their counterparts with binary circuits have become a major issue of study. A reversible circuit with equal parity of inputs and outputs is considered as a parity preserving circuit. In such circuits any fault effecting only one logical signal, is detectable at the main outputs. A new 5
Keywords: reversible logic; half adder/subtractor; full adder/subtractor; parity preserving; quantum cost; garbage outputs; constant inputs; circuit dimensions.
A Novel Fuzzy Clustering based System for Medical Image Segmentation
by B.S. Harish, S.V. ARUNA KUMAR, P. Shivakumara
Abstract: Segmenting region of interest in medical images is challenging because\r\nmedical image suffers from noise, degradation due environment influence and low resolution due to devices etc. In this paper, we have developed a novel idea based on Weighted Spatial Kernel FCM clustering for segmenting region of interest in the medical images. Unlike, traditional methods ignore spatial information, we propose a new robust system that explores spatial information to remove uncertainty in identifying accurate region in the medical images. Furthermore, the proposed method estimates the weights for spatial information to derive precise membership function to segment the region based on Gaussian kernel as distance metric.We conducted experiments on standard datasets, namely MRI Brian image dataset and evaluated performance of the proposed method using recall, precision and f-measure. Experimental results reveals that, the proposed method performs better compared to existing methods.
Keywords: Clustering; Fuzzy C-Means; Medical Images; Segmentation.
Assessment of Cloud Computing Adoption Models in E-government Environment.
by Khaled Ali, Sherif Mazen, Ehab Hassanein
Abstract: Nowadays many developing countries are experiencing revolution in e-government to deliver fluent and simple services for their citizens. However, governmental sectors face many challenges in using its e-governments services and its infrastructure, improving current services or developing new services; as data and applications increasingly inflating, IT budget costs, software licensing and support and difficulties in migration, integration and management for software and hardware. These challenges may lead to failure of e-governments projects. Therefore, there is a need for a solution to overcome these challenges. Cloud Computing plays a vital role to solve these problems. So, some of governments are now tending to adopt cloud computing in their agencies for utilizing their benefits and overcome on e-government challenges.
This paper demonstrates cloud computing, its characteristics, basic delivery models and deployment models. It analyzes and reviews the literature proposed models of cloud computing adoption in e-government environment. Finally, it compares between these models and classifies it to different classifications from functionally perspective.
Keywords: Cloud computing models; E-government; Influential factors; Cloud readiness; Services readiness.
Adaptive Artificial Chemistry for Nash Equilibria Approximation
by Rodica Ioana Lung
Abstract: A simple Artificial Chemistry model designed for computing Nash Equilibria of continuous games, called Adaptive Artificial Chemistry for Nash Equilibria is presented. This method mimicks elementary chemical reactions between molecules representing strategy profiles of a non-cooperative game while using a generative relation for Nash Equilibria in order to direct the search towards the equilibrium. Experimental results - indicating the potential of the proposed method - are performed on Cournot oligopolies for up to 1000 players.
Keywords: Cournot oligopoly; Nash equilibrium; Artificial Chemistry.
A Constraint-Based Job Recommender System Integrating FoDRA
by Nikolaos Almalis
Abstract: We present a framework for a Constraint-Based Recommender System that matches available job positions with job seekers. Our framework utilizes the Four Dimensions Recommendation Algorithm (FoDRA) in which a job attribute (e.g. age of candidate) can be modeled in four classes: exact value (E), a range with lower limit (L), a range with upper limit (U) and a range with both lower and upper limit (LU). FoDRA allows us to better formulate the job seeking and recruiting domain in a computational form. We describe both the system architecture in a high-level and the algorithm formulation of the job seeking and recruiting domain required by FoDRA. Our framework is validated through comparative experiments with real data obtained from the website of Kaggle.
Keywords: Constraint-based; Recommender System; Job Recommender; Job seeking and recruiting; Matching people and jobs; Recommendation algorithm.
Special Issue on: IEEE IWCIA2016 Innovative Computational Intelligence Methods for Data Sciences and Applications
Fine Tuning of Adaptive Learning of Deep Belief Network for Misclassification and its Knowledge Acquisition
by Shin Kamada, Takumi Ichimura
Abstract: The adaptive structure learning method of Restricted Boltzmann Machine (RBM) enables the self-organized structure during learning phase that generates appropriate neurons or annihilate a redundant neuron according to the given data space of input patterns. We have proposed the adaptive structural learning of Deep Belief Network (DBN) that realizes the assemble process with pre-trained adaptive learning of RBMs. Our proposed method can score a great success for not only 100$%$ classification capability to the training set but also high classification performance to the test set on big data benchmark test such as CIFAR-10 and CIFAR-100. However, the method may not classify the unknown data such as test data set perfectly. One of reasons is the difficulty in finding the optimal parameters to classify ambiguous patterns correctly. For other reasons, the input data with ambiguous patterns including major features in an image lead the classification to the wrong judgment. In such a case, the fine tuning method that patches a part of network signal flow based on the knowledge from the trained network will be helpful even in terms of both the improvement of classification capability and the reduction of computational cost by learning again. Therefore, we visualized the network signal patterns for a given misclassified pattern. Some characteristic signal patterns were found by the visual observations. From the observation, some kinds of rules were extracted as knowledge and they were embedded into the classification algorithm of the trained DBN. As a result, the classification capability can achieve a great success (98.6% and 85.6% to unknown data set on CIFAR-10 and CIFAR-100).
Keywords: Deep Learning; Big Data; Deep Belief Network; Adaptive Structure Learning Method; Fine Tuning; Knowledge Acquisition.
Adaptive Distributed Modified Extremal Optimization for Maximizing Contact Map Overlap and Its Performance Evaluation
by Keiichi Tamura, Hajime Kitakami, Tatsuhiro Sakai
Abstract: Identifying similarities between protein structures has received considerable attention in the post-genome era. Protein structure alignment, which is similar to sequence alignment, can identify the structural homology between two protein structures according to their three-dimensional conformations. A protein is a sequence of amino acids and each amino acid represents its residue; therefore, a protein is a sequence of residues. A sequence of residues forms complex shapes in three dimensional space, and its structure varies according to molecular dynamics. Protein structure alignment involves mapping the resides in two proteins. Maximizing the contact map overlap (CMO) problem is one of the simplest yet most robust techniques for finding optimal protein structure alignment. This optimization is known as the CMO problem, and is also known as NP-hard. Therefore, approximate approaches have been proposed for the CMO problem. We have been developing bio-inspired heuristics using distributed modified extremal optimization (DMEO) for the CMO problem. DMEO is inspired by distributed genetic algorithms, which are known as island models in evolutionary computation. DMEO is a hybrid of population-based modified extremal optimization (PMEO) and the island model. In our previous work, we proposed a DMEO-based bio-inspired heuristic, i.e., DMEO with different evolutionary strategies (DMEODES) to maintain the population diversity of evolution. DMEODES is based on the island model; moreover, some of the islands, called hot-spot islands, have a different evolutionary strategy. DMEODES efficiently maintains population diversity; however, once the population falls into local optimal solutions, there is no mechanism for getting out of them. In this paper, we propose a novel heuristic model to improve the DMEO's ability to prevent evolution stagnation. The new model integrates an adaptive generation alternation mechanism in DMEO called ADMEO. To evaluate ADMEO, we used actual protein structures. The experimental results show that ADMEO outperforms DMEODES.rn
Keywords: Contact map maximization problem; Extremal optimization; Distributed extremal optimization; Bio-inspired heuristic; Island model.
Portfolio theory application to prediction correction of train arrival times
by Takaaki Yamada, Tatsuhiro Sato
Abstract: The application of portfolio theory to the prediction of train arrival times is shown to improve prediction accuracy. The portfolio comprises two correction methods based on a Wiener process: one uses history data for the current day and the other uses data for previous days. The error between the predicted with a local model and actual time is assumed to have a normal distribution. The history data is used after statistically cleaned. Portfolio theory is used to determine the optimal application of the two methods to the correction process. Simulation using actual dense schedule of train showed that the average error in the predicted arrival time was reduced to 3 s from 12 s using history data, which had properties of railway line direction, time zone, and station. An efficient portfolio can reduce effect of an unexpected occurrence and suppress the variance in prediction errors. This error reduction will, for example, improve the efficiency of use of regenerative braking system, in which the kinetic energy of an arriving (braking) train is electrically transmitted to a departing (accelerating) train.
Keywords: railway; train arrival time; prediction correction; prediction accuracy; portfolio theory; portfolio optimization.
An FCA Approach to Mining Quantitative Association Rules from Multi-Relational Data
by Masahiro Nagao, Hirohisa Seki
Abstract: In this paper, we propose an algorithm for mining quantitative association rules (ARs) from a multi-relational database (MRDB). A MRDB contains multiple tables (relations), and attributes in a table are either categorical or quantitative (or numerical). To handle numerical data in a pattern, we consider (logical) conjunctions with interval constraints, using the notion of closed interval patterns (CIPs) proposed by Kaytoue et al. in FCA (Formal Concept Analysis). We then present an algorithm for mining strong quantitative ARs, namely they satisfy both a minimum support and a minimum confidence. We also propose a pruning method tailored to computing CIPs in an AR. We give some experimental results, which show the effectiveness of the proposed method, compared with the conventional methods such as a discretization-based approach or an optimization-based approach.
Keywords: Multi-Relational Data Mining; Closed Patterns; Quantitative Association Rules; FCA; ILP.
Particle Swarm Optimization with Dynamic Search Strategies Based on Rank Correlation
by Jun-ichi Kushida
Abstract: The paper presents particle swarm optimization with dynamic search strategies (DSS-PSO). In order to control search strategies, we introduce landscape modality estimation method using correlation coefficients between rankings of search points to PSO. This estimation method utilizes relationship between fitness and distance to a reference points. Our proposal method can switch the strategies properly according to the landscape modality estimation of an objective function. If the landscape modality is estimated as multi-modal, Elitist Learning Strategy is performed. If the landscape modality is estimated as ridge, Multi-dimensional Mutation and Mutation by Differential Vector are performed. Furthermore, inertia weight for velocity vector is controlled according to the estimated landscape modality. To confirm the search ability of the proposal method, we conducted experiments using standard benchmark functions. The experimental results show that the proposal method outperforms other PSO variants.
Keywords: Particle Swarm Optimization; Landscape Modality; Spearman’s Rank Correlation.
Special Issue on: Computational Intelligent Systems for Smart Life
Intelligent Comfort Management Agent for Smart Residential Buildings using an Updated Q Learning Algorithm
by Jayashree Subramanian, Britto Antony
Abstract: Development of smart environments is one of the hot researching fields of this digital era. The goal of the presented work is to investigate the applicability of reinforcement learning technique for designing intelligent comfort management systems of smart residences which considers minimizing the electricity consumption as its hidden agenda while maintaining maximum comfort of the occupants. Accurate occupancy estimation of a smart homes equipped with ambient sensing is expected to give vital inputs to intelligent appliance scheduling algorithms. The proposed Q learning based Intelligent Comfort Management Agent (Q-ICMA) dynamically estimates the occupancy level of the given smart space through ambient sensors embedded in the environment and then utilizes this information to drive the environment to the optimum region by automatically controlling the lighting and ventilation systems using Q learning algorithm. Simulation results show that the ε updated Q learning based agent achieves the best possible results in terms of maximum rewards and faster convergence in achieving the desired goal state.
Keywords: Comfort Management; Ambient Intelligence; Occupancy Estimation; Reinforcement Learning; Q learningrn.
Intelligent Information System to Ensure Quality in Higher Education Institutions, Towards an Automated E-University
by Mohamed Elhoseny, Noura Metawa, Ashraf Darwish, Aboul Ella Hassanien
Abstract: Despite great efforts to assure quality in higher education institutions, the ambiguity of its related concepts and requirements constitute a big challenge when trying to implement it as an intelligent information system. The present work introduces a framework for an intelligent information system that manages the quality assurance in higher educations institutions. The aim of designing such a system is to provide an automation tool that avoids unnecessary and redundant tasks associated to quality in higher education institutions. In addition, the proposed system helps all higher education stockholders to handle and monitor their tasks. Moreover, it aims to help the quality assurance units in a higher education institution to apply their qualitys standards, and to make sure that they are being maintained and enhanced. This information system contains a core module and 17 sub-modules, which are described in detail. Finally, the characteristics and components of each of these sub-modules are also discussed.
Keywords: Intelligent Information System; Quality Management Process; E-learning; E-university.
A Secure ID-based Signcryption Scheme Based on Elliptic Curve Cryptography
by Biswojit Nayak
Abstract: Signcryption is a cryptographic primitive which at the same time give both the capacity of digital signature and public key encryption in a single logical step. An Identity based cryptography is a distinct option for the traditional certificate based cryptosystem. Its principal thought is that every client utilizes his identity information as his public key. Elliptic curve cryptosystem (ECC) have new received consistent attention because of their higher security per bit as compare to other cryptosystem. This paper presents a new identity based signcryption based on elliptic curve cryptography. Its security is depends on elliptic curve discrete logarithm problem (ECDLP) and elliptic curve Diffie-Hellman problem (ECDHP). The proposed scheme can be very useful in low-end resource devices such as mobile communication, mobile banking, personal digital assistant (PDA), and Internet of Things (IoT).
Keywords: Signcryption; Elliptic Curve Cryptosystem; Private Key Generator; Public Key Infrastructure.
Intelligent Systems Based on Cloud Computing for Healthcare Services: A Survey
by Mohamed Elhoseny, Alaa Riad, Ahmed Salama, Ahmed Abdelaziz
Abstract: Cloud computing plays a very important role in healthcare services (HCS) to retrieve patients' data, diagnosis of diseases and other medical fields in less time and less of cost. This paper presents a survey of intelligent systems based on cloud environment for HCS. It reviews the uses of intelligent techniques such as genetic algorithm (GA), particle swarm optimization (PSO) and parallel particle swarm optimization (PPSO) on cloud computing environment to enhance task scheduling, reduce execution time of requests from stakeholders (patients, doctors, nurses and eg.) and maximize of resources utilization on clouds. This paper presents evaluation criteria of selected researches based on accuracy, usability, agility and applied method. Many researches in this topic were reviewed, analyzed, summarized, and compared according to the used intelligent techniques in cloud computing, healthcare systems and the concluded results. This paper also proposes architecture for intelligent healthcare systems based on cloud computing environment.
Keywords: Cloud Computing; intelligent Systems; GA; PSO; PPSO; Healthcare Services.
Computational Intelligence in Telecommunication Networks: a Review
by Kuntal Ghosh, Avijit Paul, Amrita Mukherjee Paul, Apurba Das
Abstract: The recent increase in the demand for process optimization, something which we continually learn from the nature, help the telecommunication arena to rapidly evolve into a more scalable, dynamic and robust systematic structure. Due to high intricacy and complex dynamism in every consortium of communication topology, especially in this era of big data and IoT, traditional methods fail to provide network performance and desired throughputs accurately. Computational intelligence now-a-days become indispensable for telecommunication due to the tremendous complexity in multidimensional work space and dynamic environment. Advanced high-tech machines should have its own bio-inspired adaptive intelligence with which they will emerge as energy-efficient and sustainable alternatives for our future generations. In this paper, we try to review different evolving intelligent techniques those are implemented in variegated dimensions of optimizations in telecommunication networks.
Keywords: Telecommunication; Multi-Objective Optimization; Adaptive intelligent techniques; Network Topology; Compression; Security.
Application of Cuckoo Search in Water Quality Prediction using Artificial Neural Network
by Sankhadeep Chatterjee, Sarbartha Sarkar, Nilanjan Dey, Amira Ashour, Soumya Sen, Aboul Ella Hassanien
Abstract: Domestic and industrial pollution affected the water quality to a greater extent. Polluted water became a major reason behind several community diseases, mainly in undeveloped and developing countries. The public health condition is deteriorating and putting an extra burden of counter measures to prevent such water borne diseases from spreading. Detecting the drinking water quality can prevent such scenarios prior to the critical stage. Recent research works have achieved reasonable success in predicting the water quality by deploying several machine learning based techniques and utilizing different aspects to analyze water quality. The accuracy levels of already proposed models are to be improved, keeping in mind the sensitivity of the problem domain. In the current work, a very recently proposed Cuckoo search (CS) has been utilized to improve its performance over its traditional counterparts. The proposed model (NN-CS) gradually minimizes an objective function; namely the root mean square error (RMSE) in order to find the optimal weight vector for the artificial neural network (ANN). The proposed model was compared with three other well-established models, namely NN-GA (ANN trained with Genetic Algorithm) and NN-PSO (ANN trained with Particle Swarm Optimization) in terms of accuracy, precision, recall, F-Measure, Matthews correlation coefficient (MCC) and Fowlkes-Mallows index (FM index). The simulation results established superior accuracy of NN-CS over the other models.
Keywords: Artificial Neural Network; Genetic Algorithm; Particle Swarm Optimization; Cuckoo Search; Water Quality Prediction.
Trust-based Security Models in Wireless Sensor Networks: A Survey
by Sarah Abdelwahab, Tarek Gaber
Abstract: One of the major challenges facing Wireless Sensor Networks (WSNs) today is the security. The deployment of sensor nodes is usually done in an unattended or hostile environment. This makes the networks susceptible to various threats and attacks. It is known that resources of sensor nodes suffer from different limitations such as battery life, computational capabilities and memory. Such limitations make the employment of conventional security solutions impractical. Thus, another non-conventional solution, such trust-based security, has been suggested as an effective way to secure WSNs. Recently, many trust management models for securing WSNs have been proposed. They basically detect malicious/misbehaved nodes through calculating and evaluating trustworthiness of all nodes in the network. In this paper, a survey about different WSNs trust model is presented. These models are described and discussed in terms of network architectures, adopted applications, used trust management schemes, and applied trust computation methodologies. Also comparisons among these different models are conducted under defined a set of criteria to evaluate their strengths and weaknesses. Last but not least, a discussion of the findings is also given.
Keywords: Wireless Sensor Networks; Security; Trust; Trust management scheme; Trust Methodology; Trust metrics; Trust Model.
Special Issue on: IEEE IWCIA2016 Innovative Computational Intelligence Methods for Data Sciences and Applications
Altruistic Behaviors Based Recommendation System of Tourist Information from Smartphone Application to SNS Community
by Takumi Ichimura, Takuya Uemoto, Shin Kamada
Abstract: We have already developed the recommendation system of sightseeing information on SNS by using smartphone based user participatory sensing system. Our smartphone application can collect tourist subjective data which includes jpeg files with GPS, geographic location name, the evaluation, and comments written in natural language at sightseeing spot. The system can post the attractive information for tourists to the specified Facebook page directly by our developed smartphone application. Moreover, the system can recommend the sightseeing spot and the local food corresponded to the user's feeling which can be estimated at the sightseeing spot by Emotion Generating Calculations (EGC). The users in Facebook, who are interested in sightseeing, can come to crowd the posted articles at the cyber space. However, the current activities in the SNS community are only supported by the specified people called a hub. We proposed the method of vitalization of tourist behaviors to give a stimulus to the Facebook users. We developed the simulation system for multi agent system with altruistic behaviors inspired by the Army Ants. The army ant takes feeding action with altruistic behaviors to suppress selfish behavior to a common object. In this paper, we introduced the altruism behavior determined by some simulation to vitalize the SNS community. The efficiency of the revitalization process of the community was investigated by some experimental simulation results.
Keywords: Altruism Behavior; Army Ant System; Social Network; Sightseeing Vitalization; Smartphone Application.