Cooperation between expert knowledge and data mining discovered knowledge: Lessons learned

Expert systems are built from knowledge traditionally elicited from the human expert. It is precisely knowledge elicitation from the expert that is the bottleneck in expert system construction. On the other hand, a data mining system, which automatically extracts knowledge, needs expert guidance on the successive decisions to be made in each of the system phases. In this context, expert knowledge and data mining discovered knowledge can cooperate, maximizing their individual capabilities: data mining discovered knowledge can be used as a complementary source of knowledge for the expert system, whereas expert knowledge can be used to guide the data mining process. This article summarizes different examples of systems where there is cooperation between expert knowledge and data mining discovered knowledge and reports our experience of such cooperation gathered from a medical diagnosis project called Intelligent Interpretation of Isokinetics Data, which we developed. From that experience, a series of lessons were learned throughout project development. Some of these lessons are generally applicable and others pertain exclusively to certain project types.

Protein phosphatase 2A is required for the initiation of chromosomal DNA replication

Protein phosphatase 2A (PP2A) is an abundant, multifunctional serine/threonine-specific phosphatase that stimulates simian virus 40 DNA replication. The question as to whether chromosomal DNA replication also depends on PP2A was addressed by using a cell-free replication system derived from Xenopus laevis eggs. Immunodepletion of PP2A from Xenopus egg extract resulted in strong inhibition of DNA replication. PP2A was required for the initiation of replication but not for the elongation of previously engaged replication forks. Therefore, the initiation of chromosomal DNA replication depends not only on phosphorylation by protein kinases but also on dephosphorylation by PP2A.

The replication initiation protein of the broad-host-range plasmid RK2 is activated by the ClpX chaperone

Initiation and control of replication of the broad-host-range plasmid RK2 requires two plasmid-encoded elements, the replication origin (oriV) and the initiation protein TrfA. Purified TrfA is largely in the form of a dimer; however, only the monomeric form of the protein can bind specifically to the direct repeats (iterons) at the RK2 origin. The largely dimeric form of wild-type TrfA is inactive in the initiation of replication of RK2 in an in vitro replication system reconstituted from purified components. However, preincubation of the TrfA protein with the ClpX molecular chaperone isolated from Escherichia coli activates the initiator protein for replication in the purified system. We further observed that ClpX, in an ATP-dependent reaction, greatly increases the proportion of TrfA monomers and, therefore, the ability of this protein to bind to iterons localized within RK2 origin. Finally, a copy-up mutant of the TrfA protein which is largely in the monomer form is active in the reconstituted in vitro replication system, and its activity is not affected by ClpX.

DNA polymerase ɛ is required for coordinated and efficient chromosomal DNA replication in Xenopus egg extracts

DNA polymerase ɛ (Polɛ) is thought to be involved in DNA replication, repair, and cell-cycle checkpoint control in eukaryotic cells. Although the requirement of other replicative DNA polymerases, DNA polymerases α and δ (Polα and δ), for chromosomal DNA replication has been well documented by genetic and biochemical studies, the precise role, if any, of Polɛ in chromosomal DNA replication is still obscure. Here we show, with the use of a cell-free replication system with Xenopus egg extracts, that Xenopus Polɛ is indeed required for chromosomal DNA replication. In Polɛ-depleted extracts, the elongation step of chromosomal DNA replication is markedly impaired, resulting in significant reduction of the overall DNA synthesis as well as accumulation of small replication intermediates. Moreover, despite the decreased DNA synthesis, excess amounts of Polα are loaded onto the chromatin template in Polɛ-depleted extracts, indicative of the failure of proper assembly of DNA synthesis machinery at the fork. These findings strongly suggest that Polɛ, along with Polα and Polδ, is necessary for coordinated chromosomal DNA replication in eukaryotic cells.

Expert Opinions on Improving Femicide Data Collection across Europe: A Concept Mapping Study

Femicide, defined as the killings of females by males because they are females, is becoming recognized worldwide as an important ongoing manifestation of gender inequality. Despite its high prevalence or widespread prevalence, only a few countries have specific registries about this issue. This study aims to assemble expert opinion regarding the strategies which might feasibly be employed to promote, develop and implement an integrated and differentiated femicide data collection system in Europe at both the national and international levels. Concept mapping methodology was followed, involving 28 experts from 16 countries in generating strategies, sorting and rating them with respect to relevance and feasibility. The experts involved were all members of the EU-Cost-Action on femicide, which is a scientific network of experts on femicide and violence against women across Europe. As a result, a conceptual map emerged, consisting of 69 strategies organized in 10 clusters, which fit into two domains: “Political action” and “Technical steps”. There was consensus among participants regarding the high relevance of strategies to institutionalize national databases and raise public awareness through different stakeholders, while strategies to promote media involvement were identified as the most feasible. Differences in perceived priorities according to the level of human development index of the experts’ countries were also observed.

The design and implementation of a repository for the management of spatial data integrity constraints

This paper reviews the key features of an environment to support domain users in spatial information system (SIS) development. It presents a full design and prototype implementation of a repository system for the storage and management of metadata, focusing on a subset of spatial data integrity constraint classes. The system is designed to support spatial system development and customization by users within the domain that the system will operate.

Diagnosis of diabetes mellitus: case of different cutoff values: A data mining approach

Objective: An estimation of cut-off points for the diagnosis of diabetes mellitus (DM) based on individual risk factors. Methods: A subset of the 1991 Oman National Diabetes Survey is used, including all patients with a 2h post glucose load >= 200 mg/dl (278 subjects) and a control group of 286 subjects. All subjects previously diagnosed as diabetic and all subjects with missing data values were excluded. The data set was analyzed by use of the SPSS Clementine data mining system. Decision Tree Learners (C5 and CART) and a method for mining association rules (the GRI algorithm) are used. The fasting plasma glucose (FPG), age, sex, family history of diabetes and body mass index (BMI) are input risk factors (independent variables), while diabetes onset (the 2h post glucose load >= 200 mg/dl) is the output (dependent variable). All three techniques used were tested by use of crossvalidation (89.8%). Results: Rules produced for diabetes diagnosis are: A- GRI algorithm (1) FPG>=108.9 mg/dl, (2) FPG>=107.1 and age>39.5 years. B- CART decision trees: FPG >=110.7 mg/dl. C- The C5 decision tree learner: (1) FPG>=95.5 and 54, (2) FPG>=106 and 25.2 kg/m2. (3) FPG>=106 and =133 mg/dl. The three techniques produced rules which cover a significant number of cases (82%), with confidence between 74 and 100%. Conclusion: Our approach supports the suggestion that the present cut-off value of fasting plasma glucose (126 mg/dl) for the diagnosis of diabetes mellitus needs revision, and the individual risk factors such as age and BMI should be considered in defining the new cut-off value.

Digital control system programming from process control diagrams

A graphical process control language has been developed as a means of defining process control software. The user configures a block diagram describing the required control system, from a menu of functional blocks, using a graphics software system with graphics terminal. Additions may be made to the menu of functional blocks, to extend the system capability, and a group of blocks may be defined as a composite block. This latter feature provides for segmentation of the overall system diagram and the repeated use of the same group of blocks within the system. The completed diagram is analyzed by a graphics compiler which generates the programs and data structure to realise the run-time software. The run-time software has been designed as a data-driven system which allows for modifications at the run-time level in both parameters and system configuration. Data structures have been specified to ensure efficient execution and minimal storage requirements in the final control software. Machine independence has been accomodated as far as possible using CORAL 66 as the high level language throughout the entire system; the final run-time code being generated by a CORAL 66 compiler appropriate to the target processor.

Transmission of data under multipath transmission conditions

The explosive growth in microprocessor technology and the increasing use of computers to store information has increased the demand for data communication channels. Because of this, data communication to mobile vehicles is increasing rapidly. In addition, data communication is seen as a method of relieving the current congestion of mobile radio telephone bands in the U.K. Highly reliable data communication over mobile radio channels is particularly difficult to achieve, primarily due to fading caused by multipath interference. In this thesis a data communication system is described for use over radio channels impaired by multipath interference. The thesis first describes radio communication in general, and multipath interference In particular. The practical aspects of fading channels are stressed because of their importance in the development of the system. The current U.K. land mobile radio scene is then reviewed, with particular emphasis on the use of existing mobile radio equipment for data communication purposes. The development of the data communication system is then described. This system is microprocessor based and uses an advanced form of automatic request repeat (ARQ) operation. It can be configured to use either existing radio-telephone equipment, totally new equipment specifically designed for data communication, or any combination of the two. Due to its adaptability, the system can automatically optimise itself for use over any channel, even if the channel parameters are changing rapidly. Results obtained from a particular implementation of the system, which is described in full, are presented. These show how the operation of the system has to change to accomodate changes in the channel. Comparisons are made between the practical results and the theoretical limits of the system.

Exploratory database visualisation: the application and assessment of data and dimensionality reduction

This thesis describes the development of a complete data visualisation system for large tabular databases, such as those commonly found in a business environment. A state-of-the-art 'cyberspace cell' data visualisation technique was investigated and a powerful visualisation system using it was implemented. Although allowing databases to be explored and conclusions drawn, it had several drawbacks, the majority of which were due to the three-dimensional nature of the visualisation. A novel two-dimensional generic visualisation system, known as MADEN, was then developed and implemented, based upon a 2-D matrix of 'density plots'. MADEN allows an entire high-dimensional database to be visualised in one window, while permitting close analysis in 'enlargement' windows. Selections of records can be made and examined, and dependencies between fields can be investigated in detail. MADEN was used as a tool for investigating and assessing many data processing algorithms, firstly data-reducing (clustering) methods, then dimensionality-reducing techniques. These included a new 'directed' form of principal components analysis, several novel applications of artificial neural networks, and discriminant analysis techniques which illustrated how groups within a database can be separated. To illustrate the power of the system, MADEN was used to explore customer databases from two financial institutions, resulting in a number of discoveries which would be of interest to a marketing manager. Finally, the database of results from the 1992 UK Research Assessment Exercise was analysed. Using MADEN allowed both universities and disciplines to be graphically compared, and supplied some startling revelations, including empirical evidence of the 'Oxbridge factor'.

Quantifying uncertainty in citizen weather data

The sheer volume of citizen weather data collected and uploaded to online data hubs is immense. However as with any citizen data it is difficult to assess the accuracy of the measurements. Within this project we quantify just how much data is available, where it comes from, the frequency at which it is collected, and the types of automatic weather stations being used. We also list the numerous possible sources of error and uncertainty within citizen weather observations before showing evidence of such effects in real data. A thorough intercomparison field study was conducted, testing popular models of citizen weather stations. From this study we were able to parameterise key sources of bias. Most significantly the project develops a complete quality control system through which citizen air temperature observations can be passed. The structure of this system was heavily informed by the results of the field study. Using a Bayesian framework the system learns and updates its estimates of the calibration and radiation-induced biases inherent to each station. We then show the benefit of correcting for these learnt biases over using the original uncorrected data. The system also attaches an uncertainty estimate to each observation, which would provide real world applications that choose to incorporate such observations with a measure on which they may base their confidence in the data. The system relies on interpolated temperature and radiation observations from neighbouring professional weather stations for which a Bayesian regression model is used. We recognise some of the assumptions and flaws of the developed system and suggest further work that needs to be done to bring it to an operational setting. Such a system will hopefully allow applications to leverage the additional value citizen weather data brings to longstanding professional observing networks.

Mitigating inconsistencies by coupling data cleaning, filtering, and contextual data validation in wireless sensor networks

With the advent of peer to peer networks, and more importantly sensor networks, the desire to extract useful information from continuous and unbounded streams of data has become more prominent. For example, in tele-health applications, sensor based data streaming systems are used to continuously and accurately monitor Alzheimer's patients and their surrounding environment. Typically, the requirements of such applications necessitate the cleaning and filtering of continuous, corrupted and incomplete data streams gathered wirelessly in dynamically varying conditions. Yet, existing data stream cleaning and filtering schemes are incapable of capturing the dynamics of the environment while simultaneously suppressing the losses and corruption introduced by uncertain environmental, hardware, and network conditions. Consequently, existing data cleaning and filtering paradigms are being challenged. This dissertation develops novel schemes for cleaning data streams received from a wireless sensor network operating under non-linear and dynamically varying conditions. The study establishes a paradigm for validating spatio-temporal associations among data sources to enhance data cleaning. To simplify the complexity of the validation process, the developed solution maps the requirements of the application on a geometrical space and identifies the potential sensor nodes of interest. Additionally, this dissertation models a wireless sensor network data reduction system by ascertaining that segregating data adaptation and prediction processes will augment the data reduction rates. The schemes presented in this study are evaluated using simulation and information theory concepts. The results demonstrate that dynamic conditions of the environment are better managed when validation is used for data cleaning. They also show that when a fast convergent adaptation process is deployed, data reduction rates are significantly improved. Targeted applications of the developed methodology include machine health monitoring, tele-health, environment and habitat monitoring, intermodal transportation and homeland security.

Large scale data processing using MapReduce

As massive data sets become increasingly available, people are facing the problem of how to effectively process and understand these data. Traditional sequential computing models are giving way to parallel and distributed computing models, such as MapReduce, both due to the large size of the data sets and their high dimensionality. This dissertation, as in the same direction of other researches that are based on MapReduce, tries to develop effective techniques and applications using MapReduce that can help people solve large-scale problems. Three different problems are tackled in the dissertation. The first one deals with processing terabytes of raster data in a spatial data management system. Aerial imagery files are broken into tiles to enable data parallel computation. The second and third problems deal with dimension reduction techniques that can be used to handle data sets of high dimensionality. Three variants of the nonnegative matrix factorization technique are scaled up to factorize matrices of dimensions in the order of millions in MapReduce based on different matrix multiplication implementations. Two algorithms, which compute CANDECOMP/PARAFAC and Tucker tensor decompositions respectively, are parallelized in MapReduce based on carefully partitioning the data and arranging the computation to maximize data locality and parallelism.

Mitigating Inconsistencies by Coupling Data Cleaning, Filtering, and Contextual Data Validation in Wireless Sensor Networks

With the advent of peer to peer networks, and more importantly sensor networks, the desire to extract useful information from continuous and unbounded streams of data has become more prominent. For example, in tele-health applications, sensor based data streaming systems are used to continuously and accurately monitor Alzheimer's patients and their surrounding environment. Typically, the requirements of such applications necessitate the cleaning and filtering of continuous, corrupted and incomplete data streams gathered wirelessly in dynamically varying conditions. Yet, existing data stream cleaning and filtering schemes are incapable of capturing the dynamics of the environment while simultaneously suppressing the losses and corruption introduced by uncertain environmental, hardware, and network conditions. Consequently, existing data cleaning and filtering paradigms are being challenged. This dissertation develops novel schemes for cleaning data streams received from a wireless sensor network operating under non-linear and dynamically varying conditions. The study establishes a paradigm for validating spatio-temporal associations among data sources to enhance data cleaning. To simplify the complexity of the validation process, the developed solution maps the requirements of the application on a geometrical space and identifies the potential sensor nodes of interest. Additionally, this dissertation models a wireless sensor network data reduction system by ascertaining that segregating data adaptation and prediction processes will augment the data reduction rates. The schemes presented in this study are evaluated using simulation and information theory concepts. The results demonstrate that dynamic conditions of the environment are better managed when validation is used for data cleaning. They also show that when a fast convergent adaptation process is deployed, data reduction rates are significantly improved. Targeted applications of the developed methodology include machine health monitoring, tele-health, environment and habitat monitoring, intermodal transportation and homeland security.