International Journal of Data Mining, Modelling and Management http://www.inderscience.com/browse/index.php?journalID=342&year=2012&vol=4&issue=1 Inderscience Publishers Ltd en-uk International Journal of Data Mining, Modelling and Management 1759-1163 1759-1171 © 2012 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijdmmm_scoverijdmmm.jpg http://www.inderscience.com/browse/index.php?journalID=342&year=2012&vol=4&issue=1 http://www.inderscience.com/link.php?id=45134 A key problem in multi-agent systems is represented by communication difficulties among agents having different ontologies. Since, in many cases, the presence of a unique, common ontology does not seem a suitable solution, some approaches have been proposed in the past to provide each user with his own personal ontology. These approaches face possible communication problems by means of a multilateral semantic negotiation. Although effective, this solution reduces its efficiency drastically when the agent community becomes large. This paper proposes a new solution, based on bilateral semantic negotiation, to support agent communication and the consequent ontology enrichment. This solution maintains the effectiveness of multilateral semantic negotiation and, at the same time, reduces the required costs. Bilateral semantic negotiation: a decentralised approach to ontology enrichment in open multi-agent systems
Pasquale De Meo; Giovanni Quattrone; Domenico Rosaci; Domenico Ursino
International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 1 - 38
A key problem in multi-agent systems is represented by communication difficulties among agents having different ontologies. Since, in many cases, the presence of a unique, common ontology does not seem a suitable solution, some approaches have been proposed in the past to provide each user with his own personal ontology. These approaches face possible communication problems by means of a multilateral semantic negotiation. Although effective, this solution reduces its efficiency drastically when the agent community becomes large. This paper proposes a new solution, based on bilateral semantic negotiation, to support agent communication and the consequent ontology enrichment. This solution maintains the effectiveness of multilateral semantic negotiation and, at the same time, reduces the required costs.

]]> 10.1504/IJDMMM.2012.045134 International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 1 - 38 Pasquale De Meo; Giovanni Quattrone; Domenico Rosaci; Domenico Ursino Dipartimento di Fisica, Sezione di Informatica, Università di Messina, Viale F. Stagno D'Alcontres, 31, 98166 Messina, Italy. ' DIMET, Università 'Mediterranea' di Reggio Calabria, Via Graziella, Località Feo di Vito, 89122 Reggio Calabria, Italy. ' DIMET, Università 'Mediterranea' di Reggio Calabria, Via Graziella, Località Feo di Vito, 89122 Reggio Calabria, Italy. ' DIMET, Università 'Mediterranea' di Reggio Calabria, Via Graziella, Località Feo di Vito, 89122 Reggio Calabria, Italy multi-agent systems MAS bilateral semantic negotiation agent ontology enrichment agent-based systems agent communication. 2012-01-27T23:20:50-05:00 4 1 1 38 2012-01-27T23:20:50-05:00 http://www.inderscience.com/link.php?id=45135 While data mining made inroads into the diverse areas it also entails violation of individual privacy leading to legal complications in areas like medicine and finance as consequently, privacy preserving data mining (PPDM) emerged as a new area. To achieve an equitable solution to this problem, data owners must not only preserve privacy and but also guarantee valid data mining results. This paper proposes a novel particle swarm optimisation (PSO) trained auto associative neural network (PSOAANN) for privacy preservation. Then, decision tree and logistic regression are invoked for data mining purpose, leading to PSOAANN + DT and PSOAANN + LR hybrids. The efficacy of hybrids is tested on five benchmark and four bankruptcy datasets. The results are compared with those of Ramu and Ravi (2009) and others. It was observed that the proposed hybrids yielded better or comparable results. We conclude that PSOAANN can be used as viable approach for privacy preservation. Privacy preserving data mining using particle swarm optimisation trained auto-associative neural network: an application to bankruptcy prediction in banks
Paramjeet; V. Ravi; Naveen Nekuri; Chillarige Raghavendra Rao
International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 39 - 56
While data mining made inroads into the diverse areas it also entails violation of individual privacy leading to legal complications in areas like medicine and finance as consequently, privacy preserving data mining (PPDM) emerged as a new area. To achieve an equitable solution to this problem, data owners must not only preserve privacy and but also guarantee valid data mining results. This paper proposes a novel particle swarm optimisation (PSO) trained auto associative neural network (PSOAANN) for privacy preservation. Then, decision tree and logistic regression are invoked for data mining purpose, leading to PSOAANN + DT and PSOAANN + LR hybrids. The efficacy of hybrids is tested on five benchmark and four bankruptcy datasets. The results are compared with those of Ramu and Ravi (2009) and others. It was observed that the proposed hybrids yielded better or comparable results. We conclude that PSOAANN can be used as viable approach for privacy preservation.

]]> 10.1504/IJDMMM.2012.045135 International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 39 - 56 Paramjeet; V. Ravi; Naveen Nekuri; Chillarige Raghavendra Rao Department of Humanities and Social Sciences, Indian Institute of Technology, Kharagpur-721302, India. ' Institute for Development and Research in Banking Technology, Castle Hills Road, # 1, Masab Tank, Hyderabad-500007 (AP), India. ' Institute for Development and Research in Banking Technology, Castle Hills Road, # 1, Masab Tank, Hyderabad-500007 (AP), India; Department of Computer and Information Sciences, School of MCIS, University of Hyderabad, Hyderabad-500046, AP, India. ' Department of Computer and Information Sciences, School of MCIS, University of Hyderabad, Hyderabad-500046, AP, India privacy preservation privacy protection data mining PPDM particle swarm optimisation PSO bankruptcy prediction auto-associative neural networks AANN PSOAANN logistic regression decision tree classification banks banking industry. 2012-01-27T23:20:50-05:00 4 1 39 56 2012-01-27T23:20:50-05:00 http://www.inderscience.com/link.php?id=45136 This paper proposes effective operators for cooperative genetic algorithm (CGA) to be applied to a practical nurse scheduling problem. The nurse scheduling is a very complex task. In the real hospital, the change of the schedule occurs frequently. This paper describes a technique to reoptimise such nurse schedule. CGA is superior in ability for local search, but often stagnates at the unfavourable situation because it is inferior in ability for global search. To improve this problem, we have proposed a mutation operator depending on the optimisation speed. The mutation yields small changes into the population. Then the population is able to escape from a local minimum area. However, this operator has two parameters to define itself. Therefore, we have proposed periodic mutation operator which has only one parameter. In the case which contains such changes, a more powerful operator is necessary. We propose a multi-branched mutation (MBM) operator. MBM provides natural concurrency. Therefore, we have implemented parallel processing of MBM. In many cases, when the optimisation converges on an unfavourable penalty value in the early stage of the optimisation, the final population is also unfavourable. Therefore, we propose a technique of multiplied initial populations (MIP). Effective operators using parallel processing for nurse scheduling by cooperative genetic algorithm
Makoto Ohki
International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 57 - 73
This paper proposes effective operators for cooperative genetic algorithm (CGA) to be applied to a practical nurse scheduling problem. The nurse scheduling is a very complex task. In the real hospital, the change of the schedule occurs frequently. This paper describes a technique to reoptimise such nurse schedule. CGA is superior in ability for local search, but often stagnates at the unfavourable situation because it is inferior in ability for global search. To improve this problem, we have proposed a mutation operator depending on the optimisation speed. The mutation yields small changes into the population. Then the population is able to escape from a local minimum area. However, this operator has two parameters to define itself. Therefore, we have proposed periodic mutation operator which has only one parameter. In the case which contains such changes, a more powerful operator is necessary. We propose a multi-branched mutation (MBM) operator. MBM provides natural concurrency. Therefore, we have implemented parallel processing of MBM. In many cases, when the optimisation converges on an unfavourable penalty value in the early stage of the optimisation, the final population is also unfavourable. Therefore, we propose a technique of multiplied initial populations (MIP).

]]> 10.1504/IJDMMM.2012.045136 International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 57 - 73 Makoto Ohki Tottori University, 4, 101 Koyama-Minami, Tottori, Tottori 680-8552, Japan nurse scheduling cooperative genetic algorithms CGAs mutation operator multi-branched mutation MBM multiplied initial populations MIP parallel processing hospital nurses healthcare management. 2012-01-27T23:20:50-05:00 4 1 57 73 2012-01-27T23:20:50-05:00 http://www.inderscience.com/link.php?id=45137 Centrifugal pumps are a crucial part of many industrial plants. Early detection of faults in pumps can increase their reliability, reduce energy consumption, service and maintenance costs, and increase their life-cycle and safety, thus providing a significant reduction in life-time costs. Vibration-based condition monitoring and analysis using machine learning approach is gaining momentum. Vibration monitoring can identify a number of potential pump problems such as bearing fault, impeller fault, seal fault, loose joints or fasteners, and cavitation issues. This paper compares the fault classification efficiency of standalone decision tree classifier, standalone rough set classifier with hybrid systems such as decision tree-fuzzy classifier and rough set-fuzzy classifier. The results obtained using standalone systems are compared with the performance of hybrid systems. It is observed that standalone systems outperform the hybrid systems. Application of standalone system and hybrid system for fault diagnosis of centrifugal pump using time domain signals and statistical features
N.R. Sakthivel; Binoy B. Nair; V. Sugumaran; Rajakumar S. Roy
International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 74 - 104
Centrifugal pumps are a crucial part of many industrial plants. Early detection of faults in pumps can increase their reliability, reduce energy consumption, service and maintenance costs, and increase their life-cycle and safety, thus providing a significant reduction in life-time costs. Vibration-based condition monitoring and analysis using machine learning approach is gaining momentum. Vibration monitoring can identify a number of potential pump problems such as bearing fault, impeller fault, seal fault, loose joints or fasteners, and cavitation issues. This paper compares the fault classification efficiency of standalone decision tree classifier, standalone rough set classifier with hybrid systems such as decision tree-fuzzy classifier and rough set-fuzzy classifier. The results obtained using standalone systems are compared with the performance of hybrid systems. It is observed that standalone systems outperform the hybrid systems.

]]> 10.1504/IJDMMM.2012.045137 International Journal of Data Mining, Modelling and Management, Vol. 4, No. 1 (2012) pp. 74 - 104 N.R. Sakthivel; Binoy B. Nair; V. Sugumaran; Rajakumar S. Roy Department of Mechanical Engineering, Amrita School of Engineering, Ettimadai, Amrita Vishwa Vidyapeetham, Coimbatore, Tamilnadu, 641105, India; Karpagam University, Eachanari Post, Coimbatore, Tamilnadu, 641021, India. ' Department of Electronics and Communication Engineering, Amrita School of Engineering, Ettimadai, Amrita Vishwa Vidyapeetham, Coimbatore, Tamilnadu, 641105, India. ' Department of Mechanical Engineering, SRM University, SRM Nagar, Kattankulathur, Kancheepuram District, Tamil Nadu, 603 203, India. ' School of Mechanical Sciences, Karunya University, Karunya Nagar, Coimbatore, Tamilnadu, 64114, India centrifugal pumps decision tree fuzzy logic rough sets standalone systems hybrid systems fault diagnosis condition monitoring machine learning vibration monitoring fault classification. 2012-01-27T23:20:50-05:00 4 1 74 104 2012-01-27T23:20:50-05:00