Arkadiusz Lewicki

Ant based clustering of time series discrete data --- a rough set approach

This paper focuses on clustering of time series discrete data. In time series data, each instance represents a different time step and the attributes give values associated with that time. In the presented approach, we consider discrete data, i.e., the set of values appearing in a time series is finite. For ant-based clustering, we use the algorithm based on the versions proposed by J. Deneubourg, E. Lumer and B. Faieta. As a similarity measure, the so-called consistency measure defined in terms of multistage decision transition systems is proposed. A decision on raising or dropping a given episode by the ant is made on the basis of a degree of consistency of that episode with the knowledge extracted from the neighboring episodes.

Ant-Based Extraction of Rules in Simple Decision Systems over Ontological Graphs

Abstract In the paper, the problem of extraction of complex decision rules in simple decision systems over ontological graphs is considered. The extracted rules are consistent with the dominance principle similar to that applied in the dominancebased rough set approach (DRSA). In our study, we propose to use a heuristic algorithm, utilizing the ant-based clustering approach, searching the semantic spaces of concepts presented by means of ontological graphs. Concepts included in the semantic spaces are values of attributes describing objects in simple decision systems

Ant Based Clustering of Two-Class Sets with Well Categorized Objects

In the paper, a new ant based algorithm for clustering a set of well categorized objects is shown. A set of well categorized objects is characterized by high similarity of the objects within classes and relatively high dissimilarity of the objects between different classes. The algorithm is based on versions of ant based clustering algorithms proposed earlier by Deneubourg, Lumer and Faieta as well as Handl et al. In our approach, a new local function, formulas for picking and dropping decisions, as well as some additional operations are proposed to adjust the clustering process to specific data.

An Autocatalytic Emergence Swarm Algorithm in the Decision-Making Task of Managing the Process of Creation of Intellectual Capital

This paper describes proposal for the application modified Ant Colony Optimization Algorithm in the task for recruitment and selection of employees. After analyzing the combinatorial problem involving multicriterial process of recruitment and selection model proposed non-compensating its solution using the modified ACO heuristic strategy, showing a lack of opportunities to receive appropriate the resulting matrix, related to the accurate prediction of the decision at an acceptable as satisfactory for implementation only available deterministic algorithms.

The use of strategies of normalized correlation in the ant-based clustering algorithm

The article presents a new approach to the evaluation process associated with the modification of the ant-based clustering algorithm. The main aim of this study is to determine the degree of impact of the proposed changes on the results of the implemented clustering algorithm, whose task is not only to obtain the lowest intra-group variance, but also to self-determine the amount of target classes. These modifications concern both a different way of choosing the radius of perception considering the neighborhood of objects in a search decision space, as well as a use of a completely different metric than the Euclidean one for calculating the dissimilarity of objects based on the components including the normalized angular correlation of objects under consideration.

Ant based clustering of MMPI data: an experimental study

Our research concerns psychometric data coming from the Minnesota Multiphasic Personality Inventory (MMPI) test. MMPI is one of the most frequently used in clinical mental health personality tests as well as psychopathology (mental and behavioral disorders). We are developing the Copernicus system. It is a tool for the analysis of MMPI profiles of patients with mental disorders. In this system, there have been selected and implemented different quantitative groups of methods useful for differential interprofile diagnosis. In the paper, we investigate clustering of MMPI data using one of nature-inspired heuristic approaches - ant based clustering. For this approach, we test usefulness of different dissimilarity measures of MMPI profiles both standard and those defined in the professional domain literature.

Ant-Based Clustering in Delta Episode Information Systems Based on Temporal Rough Set Flow Graphs

In the paper, we focus on ant-based clustering time series data represented by means of the so-called delta episode information systems. A clustering process is made on the basis of delta representation of time series, i.e., we are interested in characters of changes between two consecutive data points in time series instead of original data points. Most algorithms use similarity measures to compare time series. In the paper, we propose to use a measure based on temporal rough set flow graphs. This measure has a probabilistic character and it is considered in terms of the Decision Theoretic Rough Set DTRS model. To perform ant-based clustering, the algorithm based on the versions proposed by J. Deneubourg, E. Lumer and B. Faieta as well as J. Handl et al. is used.

Classification of speech signals through ant based clustering of time series

Classification of speech signals in a time domain can be made through a clustering process of time windows into which examined speech signals are divided. Disturbances in speech signals of patients having some problems with the voice organ cause some difficulties in formation of coherent clusters of similar time windows. A quality of a clustering process result can be used as an indicator of non-natural disturbances in articulation of selected phonemes by patients. In the paper, we describe a procedure based on this fact. A special ant based algorithm is used to cluster time windows being time series. In this algorithm, a new local function, formulas for picking and dropping decisions as well as some additional operations are implemented to adjust the clustering process to a classification ability.

The recruitment and selection of staff problem with an Ant Colony system

This paper describes proposal for the application modified Ant Colony Optimization Algorithm in the task for recruitment and selection of employees. After analyzing the combinatorial problem involving multicriterial process of recruitment and selection model proposed non-compensating its solution using the modified ACO heuristic strategy, showing a lack of opportunities to receive appropriate the resulting matrix, related to the accurate prediction of the decision at an acceptable as satisfactory for implementation only available deterministic algorithms.

The ant colony optimization algorithm for multiobjective optimization non-compensation model problem staff selection

This paper describes proposal for the application to modify the Ant Colony Optimization for multiobjective optimization non-compensation model problem staff selection. After analyzing the combinatorial problem involving multicriterial process of recruitment and selection model, it proposed noncompensating its solution using the modified ACO heuristic strategy. This shows that the lack of opportunities to receive appropriate the resulting matrix is related to the accurate prediction of the decision at an acceptable as satisfactory for implementation only available deterministic algorithms.