Improving the Scalability of Reduct Determination in Rough Sets

Rough Set Data Analysis (RSDA) is a non-invasive data analysis approach that solely relies on the data to find patterns and decision rules. Despite its noninvasive approach and ability to generate human readable rules, classical RSDA has not been successfully used in commercial data mining and rule generating engines. The reason is its scalability. Classical RSDA slows down a great deal with the larger data sets and takes much longer times to generate the rules. This research is aimed to address the issue of scalability in rough sets by improving the performance of the attribute reduction step of the classical RSDA - which is the root cause of its slow performance. We propose to move the entire attribute reduction process into the database. We defined a new schema to store the initial data set. We then defined SOL queries on this new schema to find the attribute reducts correctly and faster than the traditional RSDA approach. We tested our technique on two typical data sets and compared our results with the traditional RSDA approach for attribute reduction. In the end we also highlighted some of the issues with our proposed approach which could lead to future research.

Minimibiolietetuottoinen aktiivilieteprosessi massateollisuuden peroksidipitoisten jätevesien puhdistuksessa

Työ on tehty USF Aquaflow Oy:lle osana Cleantech 2000-projektia. USF Aquaflow Oy on suunnitellut minimibiolietetuottoisen reaktorin, MBP-reaktorin, toimivaksi osana aktiivilieteprosessia. Työn tavoitteena oli selvittää MBP-reaktorin toimintaa massateollisuuden peroksidipitoisilla jätevesillä. Pääpaino asetettiin MBP-reaktorin mikrobiologian tutkimiseen. Aktiivilieteprosessissa syntyvä bioliete on yksi metsäteollisuuden merkittävimmistä sivuainevirroista, jonka tuotantoa pyritään vähentämään ja käsiteltävyyttä parantamaan. MBP-reaktori aktiivilieteprosessissa vähentää koko prosessin lietteentuottoa, nostaa lietteen kuiva-ainepitoisuutta ja vähentää näin lietteen vaatimaa jatkokäsittelyn tarvetta. Työssä tutkittiin kahdella erilaisella jätevesijakeella peroksidin vaikutusta MBP-reaktorin COD-reduktioon, kiintoaineen kasvuun, lietteentuottoon ja mikrobiologiaan eri pituisilla viiveillä. MBP-reaktorin viive on suunniteltu aktiivilieteprosessin ilmastusaltaan viivettä huomattavasti lyhyemmäksi. Työn tuloksien perusteella lyhyellä viiveellä MBP-reaktorissa käynnistyy tehokas bakteeritoiminta, joka kuluttaa jäteveden COD:ta. Sellutehtaan jätevesille MBP-reaktorin toiminta on heikompaa kuin termomekaanisen massanvalmistuksen jätevesillä, johtuen sellun valmistuksessa käytetyistä kemikaaleista. Jätevedenpuhdistamon lietteen määrän vähentäminen on tällä hetkellä metsäteollisuuden tehtailla tärkeä jatkotutkimuksia vaativa kohde. MBP-reaktorin toiminnan takaamiseksi osana aktiivilieteprosessia tulisi jatkotutkimuksia suorittaa eri tyyppisille jätevesijakeille ja tarkkailla useampien kemikaalien vaikutusta reaktorin mikrobiologiaan, COD-reduktioon ja lietteentuottoon.

Jalometallien pelkistyskemikaalit

Tässä työssä esitellään kirjallisuudesta löytyneitä vaihtoehtoja jalometallien (Au, Ag, Pt, Pd, Is, Os, Rh, Ru, Re) homogeeniseen pelkistämiseen ja tekijöitä, jotka vaikuttavat pelkistimen valintaan. Jalometallien korkea hinta tekee niiden talteenoton pienistäkin pitoisuuksista kiinnostavaksi. Pelkistäminen on talteenoton viimeinen vaihe, jota voidaan käyttää myös puhdistusaskeleena. Pelkistimen valinnalla on suuri merkitys pelkistystulokseen. Myös pH:lla ja lämpötilalla on merkittävä vaikutus pelkistykseen. Ideaalinen pelkistyskemikaali on edullinen, selektiivinen, sillä on kohtuullinen pelkistysaika, se ei ole haitallinen, ei muodosta haitallisia sivutuotteita ja tarvittava prosessi on yksinkertainen. Lupaavia pelkistyskemikaaleja ovat esimerkiksi askorbiinihappo, vetyperoksidi ja muurahaishappo.

Honey proteins and their interaction with polyphenols

This project aimed to determine the protein prof i les and concent rat ion in honeys, ef fect of storage condi t ions on the protein content and the interact ion between proteins and polyphenols. Thi r teen honeys f rom di f ferent botanical or igins were analyzed for thei r protein prof i les using SDS-PAGE, protein concent rat ion and phenol ic content , using the Pierce Protein Assay and Fol in-Ciocal teau methods, respectively. Protein-polyphenol interact ions were analyzed by a combinat ion of the ext ract ion of honeys wi th solvents of di f ferent polar i t ies fol lowed by LCjMS analysis of the obtained f ract ions. Results demonst rated a di f ferent protein content in the tested honeys, wi th buckwheat honey possessing the highest protein concent rat ion. We have shown that the reduct ion of proteins dur ing honey storage was caused, partially, by the protein complexat ion wi th phenolics. The LCjMS analysis of the peak elut ing at retent ion t ime of 10 to 14 min demonst rated that these phenolics included f lavonoids such as Pinobanksin, Pinobanksin acetate, Apigenin, Kaemferol and Myricetin and also cinnamic acid.

GA approach for finding Rough Set decision rules based on bireducts

Feature selection plays an important role in knowledge discovery and data mining nowadays. In traditional rough set theory, feature selection using reduct - the minimal discerning set of attributes - is an important area. Nevertheless, the original definition of a reduct is restrictive, so in one of the previous research it was proposed to take into account not only the horizontal reduction of information by feature selection, but also a vertical reduction considering suitable subsets of the original set of objects. Following the work mentioned above, a new approach to generate bireducts using a multi--objective genetic algorithm was proposed. Although the genetic algorithms were used to calculate reduct in some previous works, we did not find any work where genetic algorithms were adopted to calculate bireducts. Compared to the works done before in this area, the proposed method has less randomness in generating bireducts. The genetic algorithm system estimated a quality of each bireduct by values of two objective functions as evolution progresses, so consequently a set of bireducts with optimized values of these objectives was obtained. Different fitness evaluation methods and genetic operators, such as crossover and mutation, were applied and the prediction accuracies were compared. Five datasets were used to test the proposed method and two datasets were used to perform a comparison study. Statistical analysis using the one-way ANOVA test was performed to determine the significant difference between the results. The experiment showed that the proposed method was able to reduce the number of bireducts necessary in order to receive a good prediction accuracy. Also, the influence of different genetic operators and fitness evaluation strategies on the prediction accuracy was analyzed. It was shown that the prediction accuracies of the proposed method are comparable with the best results in machine learning literature, and some of them outperformed it.

Prediction of Key Symptoms of Learning Disabilities in School-Age Children Using Rough Sets

This paper highlights the prediction of learning disabilities (LD) in school-age children using rough set theory (RST) with an emphasis on application of data mining. In rough sets, data analysis start from a data table called an information system, which contains data about objects of interest, characterized in terms of attributes. These attributes consist of the properties of learning disabilities. By finding the relationship between these attributes, the redundant attributes can be eliminated and core attributes determined. Also, rule mining is performed in rough sets using the algorithm LEM1. The prediction of LD is accurately done by using Rosetta, the rough set tool kit for analysis of data. The result obtained from this study is compared with the output of a similar study conducted by us using Support Vector Machine (SVM) with Sequential Minimal Optimisation (SMO) algorithm. It is found that, using the concepts of reduct and global covering, we can easily predict the learning disabilities in children

Normas tributárias indutoras na concretização do princípio constitucional da redução das desigualdades sociais e regionais

The Federal Constitution states that the reduction of social and regional inequalities is one of the goals to be achieved by the Brasilian State. The economic constitution states that the national economy must be developed so as to achieve, amongst other objectives, the reduction of those inequalities. In this paper, we aim to demonstrate the duty, imposed by the Constitution to the State, of acting in the national economy so as to promote the achievement of the constitutional goals, among wich we highlight the reduction of inequalities. One of the instruments that can be used by the State to achieve this objective is its fiscal policy. It is also an aim in this paper to demonstrate that inducing tax norms can be used by the State, because it can encourage the economic agents to bring about the reduction of social and regional inequalities. Therefore, after bibliographic and jurisprudential research, we conclude that the duty, imposed to the State, of acting in the national economy so as to promote the achievement of the constitutional goals exists. We also conclude that this acting must be planed and constant, because the consequences are slow and that, within the limits of the constitution, the inducing tax norms can be an instrument for the State in order to reduct the social and regional inequalities