for Journals by Title or ISSN
for Articles by Keywords
Followed Journals
Journal you Follow: 0
Sign Up to follow journals, search in your chosen journals and, optionally, receive Email Alerts when new issues of your Followed Journals are published.
Already have an account? Sign In to see the journals you follow.
Journal Cover International Journal of Intelligent Systems Design and Computing
  [0 followers]  Follow
   Hybrid Journal Hybrid journal (It can contain Open Access articles)
   ISSN (Print) 2052-8477 - ISSN (Online) 2052-8485
   Published by Inderscience Publishers Homepage  [427 journals]
  • Design and development of web enabled fuzzy expert system using rule
           advancement strategy
    • Authors: Arun Solanki, Ela Kumar
      Pages: 3 - 27
      Abstract: This paper reports a new approach for providing intelligence in the expert system for diagnosis of diseases for rose flower. It describes the development of a web-based intelligent disease diagnosis system. This expert system is based on a fuzzy logic approach and the Euclidean distance method. This approach is based on rule advancement strategy. This approach enables the drawing of inferences with the enhanced intelligence. This approach is used in the existing fuzzy technique for inferencing in expert system. The proposed expert system incorporates new features: 1) development of knowledge management platform; 2) dynamic knowledge base creation strategy. The dynamically prompted rules are derived from those diagnosis sessions which resulted in successful decisions. This enables more efficient decision-making in the future sessions; 3) dynamic knowledge acquisition; 4) explanation facility which incorporates the rule firing history and rule explanation generator. This expert system gives an acceptable diagnosis of diseases. The inferences are drawn faster compared to traditional approaches. The proposed expert system which is based on rule advancement strategy has been tested for flower rose.
      Keywords: expert systems; dynamic knowledge base; rule advancement strategy; RAS; fuzzy logic; PHP; knowledge management platform; KMP; roses; rose diseases; flower diseases; flowers; web-based diagnosis; intelligent diagnosis; disease diagnosis; Euclidean
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 3 - 27
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082844
      Issue No: Vol. 1, No. 1/2 (2017)
  • Markov chains and linear model-based hybrid prediction algorithm for
           cognitive agents
    • Authors: Smail Tigani, Mouhamed Ouzzif, Abderrahim Hasbi
      Pages: 28 - 42
      Abstract: The aim of this work is the improvement of cognitive agents performance. An agent is designed to follow fixed instructions to reach a given goal, this can be considered a limitation of agent technology because it does not have a minimum level of intelligence. This work proposes a new algorithm able to make prediction and learn from its experience in the prediction of a supervised environment. This allows the agent to analyse the history observations and make prediction of future environment state using the designed auto-adaptive algorithm based on stochastic models. The algorithms designed in this work can be applied in optimised scheduling or random environments management.
      Keywords: agent technology; distributed systems; prediction algorithms; learning patterns; random systems; Markov chains; linear modelling; cognitive agents; stochastic modelling; multi-agent systems; MAS; agent-based systems
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 28 - 42
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082845
      Issue No: Vol. 1, No. 1/2 (2017)
  • Diagnosis of EEG-based diseases using data mining and case-based
    • Authors: Babita Pandey, Depika Kundra
      Pages: 43 - 55
      Abstract: Medical diagnosis system (MDS) provides facility to clinical experts for diagnosis of the different diseases. This paper focus on the development of the MDS for the diagnosis of electroencephalography (EEG)-based diseases, integrating J48 (data mining) and case-based reasoning (CBR). These integrated systems reduce the error amount and degree of uncertainty. Brain is the bioelectric generator. Neurological disordering in the brain leads some problems like muscle weakness and abnormal brain functioning. EEG is a medical imaging techniques that helps to measure the abnormality occurs in the electric activity of the human brain. It gives the information about the level of consciousness of the person, and also contains very useful information relating to different physiological state of brain. In this work, firstly, J48 algorithm is used for reducing the dimension of parameters. After that CBR is implemented for diagnosis of the different EEG-based diseases. The integration of J48 and CBR improves the accuracy of diagnosis and solve the problem of knowledge acquisition.
      Keywords: EEG signals; disease diagnosis; data mining; J48 algorithm; case-based reasoning; CBR; medical diagnosis; electroencephalograms; medical images; knowledge acquisition; neurological disorders
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 43 - 55
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082851
      Issue No: Vol. 1, No. 1/2 (2017)
  • Design of prisoner's dilemma-based fuzzy C-means computed torque
           controller for PUMA-560 robot manipulator
    • Authors: Ch Ravi Kumar, K.R. Sudha, D.V. Pushpalatha
      Pages: 56 - 70
      Abstract: Robots are highly nonlinear and chaotic in position control. The present paper mainly presents the position control of PUMA-560 Robot manipulator. Computed torque controller (CTC) is one of the solutions for position control of robot manipulators. The main drawback of controller is that it fails to operate under different dynamic operating conditions. To overcome this difficulty, intelligent controllers have gained importance. In this paper a novel approach, design of prisoner's dilemma-based fuzzy C-means controller to control the position of robot manipulator is presented. This controller is employed at the inputs of computed torques for obtaining the desired position. Fuzzy C-means controller with computed torques is realised by validating the clusters to choose most contributed rules. Thus the unfired rules are eliminated from the actual rule-base. Hence, a compact fuzzy controller with minimum rule-base, fuzzy C-means computed torque controller (FCMCTC), is designed. The concept of prisoner's dilemma is introduced in this paper to improve the fuzzy strategy. The interrelations between inputs and outputs of a fuzzy linguistic model are assigned using payoff matrix through prisoner's dilemma. Simulation results prove the efficacy of proposed controller when compared to proportional derivative computed torque controller (PD-CTC), normal FLC and that of the reference signal.
      Keywords: PUMA-560 robots; fuzzy C-means clustering; fuzzy clustering; phase-plane plot; prisoner's dilemma; computed torque; controller design; robot control; manipulator control; position control; intelligent control; simulation
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 56 - 70
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082852
      Issue No: Vol. 1, No. 1/2 (2017)
  • Speech recognition using deep neural network - recent trends
    • Authors: Ch Ravi Kumar, K.R. Sudha, D.V. Pushpalatha
      Pages: 71 - 86
      Abstract: Deep neural networks (DNN) are special forms of learning-based structures composed of multiple hidden layers formed by artificial neurons. These are different to the conventional artificial neural networks (ANN) and are accepted as efficient tools for solving emerging real world problems. Recently, DNNs have become a mainstream speech recognition tool and are fast becoming part of evolving technologies emerging as a viable option to replace all other leading tools so far used. ANNs with deep learning which uses a generative, layer by-layer pre-training method for initialising the weights has provided best solution for acoustic modelling for speech recognition. This paper provides a brief description of the current technology related to speech recognition and its slow adoption of DNN-based approaches. Initially, a historical note on the technology development for speech recognition system is given. The later part explains the DNN-based acoustic modelling for speech recognition and recent technology developments reported and the ones available for actual use.
      Keywords: speech recognition; artificial neural networks; ANNs; deep neural networks; DNN; acoustic modelling
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 71 - 86
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082853
      Issue No: Vol. 1, No. 1/2 (2017)
  • A new look at compactly supported biorthogonal Riesz bases of wavelets
    • Authors: Mahendra Kumar Jena, Manas Ranjan Mishra
      Pages: 87 - 106
      Abstract: In this paper, we give two algorithms to compute compactly supported biorthogonal Riesz basis of wavelets. The input to these algorithms are filters of the transfer and the dual transfer functions, which are obtained by solving the Bezout equation. This Bezout equation arises from biorthogonality of the scaling function and the dual scaling function. We solve the Bezout equation in a simple and algebraic way. We also give a case study of the biorthogonal wavelets showing their detail construction. Some references to Sobolev regularity of the wavelets which is a qualitative property of the wavelet is also made by us.
      Keywords: biorthogonal wavelets; Bezout equation; transfer function; transition operator; Riesz bases; Sobolev regularity
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 87 - 106
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082854
      Issue No: Vol. 1, No. 1/2 (2017)
  • Identity verification system: a visual cryptography-based approach to
           prevent fraudulent in admission process
    • Authors: Dhiraj Pandey, Uma Shankar Rawat
      Pages: 107 - 126
      Abstract: In today's competitive world, examinations are a means of assessing a person's potential. It is therefore important that such process be unbiased, but several cases have been encountered where candidates use proxies to write exams and score well. To deal with the same, generally we use multiple identity proofs to authenticate the candidate, which increases the privacy concern and expended on maintaining the extra data and keeping it secure. This paper introduces a novel authentication technique using bit plane-based encryption for fraud candidate detection during any stage of the selection process. Multiple visual cryptography-based method has been explored for its suitability. The effect of noise and differently chosen encryption scheme has also been observed. With the currently available infrastructure, it is quite easy to implement the proposed system for authentication of students and provide a level platform for competition.
      Keywords: visual cryptography; image encryption; identification; bit-level processing; authentication; identity verification; fraudulent admission; data security; privacy preservation; privacy protection; fraud detection; student examinations; student exam
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 107 - 126
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082855
      Issue No: Vol. 1, No. 1/2 (2017)
  • An improved extreme learning machine to classify multinomial datasets
           using particle swarm optimisation
    • Authors: Nilamadhab Dash, Rojalina Priyadarshini, Rachita Misra
      Pages: 127 - 144
      Abstract: In this paper, we propose a particle swarm-based extreme learning machine (ELM) to classify datasets with varying number of classes. This work emphasises on a couple of important parameters, like maximisation of classification accuracy and minimisation of training time. As a machine classifier, an ELM has been chosen, which is an improvement over back propagation network. For each of the input dataset an optimised target was determined by using particle swarm optimisation (PSO) technique. Those specific targets are used with the input data to train the ELM during classification process. For this, some of the benchmark classification datasets are used. To compare the proposed method and some of the existing methods an extensive experimental study has been carried out; a comparative analysis is done by taking parameters like percentage of classification accuracy, training time and complexity of the computing algorithm.
      Keywords: multinomial classification; extreme learning machines; ELM; normalisation; particle swarm optimisation; PSO; back propagation neural networks; classification accuracy; input; targets; algorithm complexity
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 127 - 144
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082856
      Issue No: Vol. 1, No. 1/2 (2017)
  • Cluster labelling using chi-square-based keyword ranking and mutual
           information score: a hybrid approach
    • Authors: Rajendra Kumar Roul, Sanjay Kumar Sahay
      Pages: 145 - 167
      Abstract: Cluster labelling is a technique which provides useful information about the cluster to the end users. In this paper, we propose a novel approach which is the follow-up of our previous work. Our earlier approach generates clusters of web documents by using a modified apriori approach which is more efficient and faster than the traditional apriori approach. To label the clusters, the proposed approach used an effective feature selection technique which selects the top features of a cluster. Rather than labelling the cluster with 'bag of words', a concept driven mechanism has been developed which uses the Wikipedia that takes the top features of a cluster as input to generate the possible candidate labels. Mutual information (MI) score technique has been used for ranking the candidate labels and then the topmost candidates are considered as potential labels of a cluster. Experimental results on two benchmark datasets demonstrate the efficiency of our approach.
      Keywords: candidate labels; chi-square; keyword ranking; mutual information score; Wikipedia; cluster labelling; web documents; feature selection
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 145 - 167
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082857
      Issue No: Vol. 1, No. 1/2 (2017)
  • Intramodal palmprint recognition using texture feature
    • Authors: Y.L. Malathi Latha, Munaga V.N.K. Prasad
      Pages: 168 - 185
      Abstract: Palmprint technology is a new branch of biometrics used to identify an individual. Palmprint has rich set of features like palm lines, wrinkles, minutiae points, texture, ridges, etc. Several line and texture extraction techniques for palmprint have been extensively studied. This paper presents an intramodal authentication system based on texture information extracted from the palmprint using the Haralick features, 2D-Gabor and 2D-log Gabor filters. An individual feature vector is computed for a palmprint using the extracted texture information of each filter type. Performance of the system using three feature types is evaluated individually. Finally, we combine the three feature types using feature level fusion to develop an intramodal palmprint recognition system. The experiments are evaluated on a standard benchmark database (PolyU Database), and the results shows that significant improvement in terms of recognition accuracy and error rates with the proposed intramodal recognition system compared to individual representations.
      Keywords: palmprints; Gabor filter; log-Gabor filter; intramodal authentication; Haralick features; feature level fusion; palmprint recognition; biometrics; texture features; feature extraction
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 168 - 185
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082858
      Issue No: Vol. 1, No. 1/2 (2017)
  • Medical device design - an introduction to systems risk
    • Authors: Y.L. Malathi Latha, Munaga V.N.K. Prasad
      Pages: 186 - 197
      Abstract: Medical devices which are developed for human application can be used for diagnostic purposes. Researchers faced with some of the complex tasks that are making a medical device safe for human use. This means that the device should be safe, accurate and cost effective risk management that involves the identification, understand, control, and prevent failures that results in hazards exposures while humans use medical devices. Risk and hazard analysis, is a structured tool for evaluating the potential problems that could lead to encountered in connection with the use of taking a drug, or using a medical device. The purpose of this paper is to discuss the importance analysis of risk analysis, application of risk management tools, and the benefit of the risk management process. The final goal is to minimise use-related hazards, assure that intended users will be able to use the medical devices safely and effectively throughout the product life cycle, and to facilitate review of new device submissions and design control documentation.
      Keywords: hazard analysis; ISO 14971; medical device design; systems risk; medical devices; risk management; risk assessment; medical safety
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 186 - 197
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082870
      Issue No: Vol. 1, No. 1/2 (2017)
  • Application of Epanechnikov kernel smoothing technique in disability data
    • Authors: Jumi Kalita, Pranita Sarmah
      Pages: 198 - 204
      Abstract: Statistical data contains noise. Smoothing is used to smooth out these noises and present the data as a meaningful one. Kernel methods are nonparametric smoothing tools that can reveal structural features in the data which may not be possible with a parametric approach. This paper applies Epanechnikov kernel method of data smoothing to smooth out the dropout rates of the children with disabilities in the special educational institutions. The continuation probabilities and dropout rates of these children in the special educational institutions are indicators of effectiveness of such education systems. The dropout rates before and after smoothing are graphically presented. The distributions of the crude and smoothed rate are examined. It has been observed that under chi-squared test the smoothed data follows log logistic distribution while the crude data follows triangular distribution.
      Keywords: dropout rates; continuation probability; Epanechnikov kernel smoothing; disability data; data smoothing; children with disabilities; special education; child disability
      Citation: International Journal of Intelligent Systems Design and Computing, Vol. 1, No. 1/2 (2017) pp. 198 - 204
      PubDate: 2017-03-14T23:20:50-05:00
      DOI: 10.1504/IJISDC.2017.082874
      Issue No: Vol. 1, No. 1/2 (2017)
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
Home (Search)
Subjects A-Z
Publishers A-Z
Your IP address:
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-2016