Predicting project performance through neural networks

Successful project delivery of construction projects depends on many factors. With regard to the construction of a facility, selecting a competent contractor for the job is paramount. As such, various approaches have been advanced to facilitate tender award decisions. Essentially, this type of decision involves the prediction of a bidderÕs performance based on information available at the tender stage. A neural network based prediction model was developed and presented in this paper. Project data for the study were obtained from the Hong Kong Housing Department. Information from the tender reports was used as input variables and performance records of the successful bidder during construction were used as output variables. It was found that the networks for the prediction of performance scores for Works gave the highest hit rate. In addition, the two most sensitive input variables toward such prediction are ‘‘Difference between Estimate’’ and ‘‘Difference between the next closest bid’’. Both input variables are price related, thus suggesting the importance of tender sufficiency for the assurance of quality production.

A fuzzy neural network approach for contractor pre-qualification

Nonlinearity, uncertainty and subjectivity are the three predominant characteristics of contractors prequalification which cause the process more of an art than a scientific evaluation. A fuzzy neural network (FNN) model, amalgamating both the fuzzy set and neural network theories, has been developed aiming to improve the objectiveness of contractor prequalification. Through the FNN theory, the fuzzy rules as used by the prequalifiers can be identified and the corresponding membership functions can be transformed. Eighty-five cases with detailed decision criteria and rules for prequalifying Hong Kong civil engineering contractors were collected. These cases were used for training (calibrating) and testing the FNN model. The performance of the FNN model was compared with the original results produced by the prequalifiers and those generated by the general feedforward neural network (GFNN, i.e. a crisp neural network) approach. Contractor’s ranking orders, the model efficiency (R2) and the mean absolute percentage error (MAPE) were examined during the testing phase. These results indicate the applicability of the neural network approach for contractor prequalification and the benefits of the FNN model over the GFNN model. The FNN is a practical approach for modelling contractor prequalification.

Decision support system for contractor pre-qualification : artificial neural network model

The selection criteria for contractor pre-qualification are characterized by the co-existence of both quantitative and qualitative data. The qualitative data is non-linear, uncertain and imprecise. An ideal decision support system for contractor pre-qualification should have the ability of handling both quantitative and qualitative data, and of mapping the complicated nonlinear relationship of the selection criteria, such that rational and consistent decisions can be made. In this research paper, an artificial neural network model was developed to assist public clients identifying suitable contractors for tendering. The pre-qualification criteria (variables) were identified for the model. One hundred and twelve real pre-qualification cases were collected from civil engineering projects in Hong Kong, and eighty-eight hypothetical pre-qualification cases were also generated according to the “If-then” rules used by professionals in the pre-qualification process. The results of the analysis totally comply with current practice (public developers in Hong Kong). Each pre-qualification case consisted of input ratings for candidate contractors’ attributes and their corresponding pre-qualification decisions. The training of the neural network model was accomplished by using the developed program, in which a conjugate gradient descent algorithm was incorporated for improving the learning performance of the network. Cross-validation was applied to estimate the generalization errors based on the “re-sampling” of training pairs. The case studies show that the artificial neural network model is suitable for mapping the complicated nonlinear relationship between contractors’ attributes and their corresponding pre-qualification (disqualification) decisions. The artificial neural network model can be concluded as an ideal alternative for performing the contractor pre-qualification task.

Generating rules with predicates, terms and variables from the pruned neural networks

Artificial neural networks (ANN) have demonstrated good predictive performance in a wide range of applications. They are, however, not considered sufficient for knowledge representation because of their inability to represent the reasoning process succinctly. This paper proposes a novel methodology Gyan that represents the knowledge of a trained network in the form of restricted first-order predicate rules. The empirical results demonstrate that an equivalent symbolic interpretation in the form of rules with predicates, terms and variables can be derived describing the overall behaviour of the trained ANN with improved comprehensibility while maintaining the accuracy and fidelity of the propositional rules.

Identification of factors predicting clickthrough in Web searching using neural network analysis

In this research, we aim to identify factors that significantly affect the clickthrough of Web searchers. Our underlying goal is determine more efficient methods to optimize the clickthrough rate. We devise a clickthrough metric for measuring customer satisfaction of search engine results using the number of links visited, number of queries a user submits, and rank of clicked links. We use a neural network to detect the significant influence of searching characteristics on future user clickthrough. Our results show that high occurrences of query reformulation, lengthy searching duration, longer query length, and the higher ranking of prior clicked links correlate positively with future clickthrough. We provide recommendations for leveraging these findings for improving the performance of search engine retrieval and result ranking, along with implications for search engine marketing

Image acquisition and manipulation protocols for CT-PET fusion to improve the accuracy of gross tumour volume localisation for 3D conformal radiotherapy for lung cancer

Aims: To develop clinical protocols for acquiring PET images, performing CT-PET registration and tumour volume definition based on the PET image data, for radiotherapy for lung cancer patients and then to test these protocols with respect to levels of accuracy and reproducibility. Method: A phantom-based quality assurance study of the processes associated with using registered CT and PET scans for tumour volume definition was conducted to: (1) investigate image acquisition and manipulation techniques for registering and contouring CT and PET images in a radiotherapy treatment planning system, and (2) determine technology-based errors in the registration and contouring processes. The outcomes of the phantom image based quality assurance study were used to determine clinical protocols. Protocols were developed for (1) acquiring patient PET image data for incorporation into the 3DCRT process, particularly for ensuring that the patient is positioned in their treatment position; (2) CT-PET image registration techniques and (3) GTV definition using the PET image data. The developed clinical protocols were tested using retrospective clinical trials to assess levels of inter-user variability which may be attributed to the use of these protocols. A Siemens Somatom Open Sensation 20 slice CT scanner and a Philips Allegro stand-alone PET scanner were used to acquire the images for this research. The Philips Pinnacle3 treatment planning system was used to perform the image registration and contouring of the CT and PET images. Results: Both the attenuation-corrected and transmission images obtained from standard whole-body PET staging clinical scanning protocols were acquired and imported into the treatment planning system for the phantom-based quality assurance study. Protocols for manipulating the PET images in the treatment planning system, particularly for quantifying uptake in volumes of interest and window levels for accurate geometric visualisation were determined. The automatic registration algorithms were found to have sub-voxel levels of accuracy, with transmission scan-based CT-PET registration more accurate than emission scan-based registration of the phantom images. Respiration induced image artifacts were not found to influence registration accuracy while inadequate pre-registration over-lap of the CT and PET images was found to result in large registration errors. A threshold value based on a percentage of the maximum uptake within a volume of interest was found to accurately contour the different features of the phantom despite the lower spatial resolution of the PET images. Appropriate selection of the threshold value is dependant on target-to-background ratios and the presence of respiratory motion. The results from the phantom-based study were used to design, implement and test clinical CT-PET fusion protocols. The patient PET image acquisition protocols enabled patients to be successfully identified and positioned in their radiotherapy treatment position during the acquisition of their whole-body PET staging scan. While automatic registration techniques were found to reduce inter-user variation compared to manual techniques, there was no significant difference in the registration outcomes for transmission or emission scan-based registration of the patient images, using the protocol. Tumour volumes contoured on registered patient CT-PET images using the tested threshold values and viewing windows determined from the phantom study, demonstrated less inter-user variation for the primary tumour volume contours than those contoured using only the patient’s planning CT scans. Conclusions: The developed clinical protocols allow a patient’s whole-body PET staging scan to be incorporated, manipulated and quantified in the treatment planning process to improve the accuracy of gross tumour volume localisation in 3D conformal radiotherapy for lung cancer. Image registration protocols which factor in potential software-based errors combined with adequate user training are recommended to increase the accuracy and reproducibility of registration outcomes. A semi-automated adaptive threshold contouring technique incorporating a PET windowing protocol, accurately defines the geometric edge of a tumour volume using PET image data from a stand alone PET scanner, including 4D target volumes.

GYAN: A methodology for rule extraction from artificial neural networks

Artificial neural network (ANN) learning methods provide a robust and non-linear approach to approximating the target function for many classification, regression and clustering problems. ANNs have demonstrated good predictive performance in a wide variety of practical problems. However, there are strong arguments as to why ANNs are not sufficient for the general representation of knowledge. The arguments are the poor comprehensibility of the learned ANN, and the inability to represent explanation structures. The overall objective of this thesis is to address these issues by: (1) explanation of the decision process in ANNs in the form of symbolic rules (predicate rules with variables); and (2) provision of explanatory capability by mapping the general conceptual knowledge that is learned by the neural networks into a knowledge base to be used in a rule-based reasoning system. A multi-stage methodology GYAN is developed and evaluated for the task of extracting knowledge from the trained ANNs. The extracted knowledge is represented in the form of restricted first-order logic rules, and subsequently allows user interaction by interfacing with a knowledge based reasoner. The performance of GYAN is demonstrated using a number of real world and artificial data sets. The empirical results demonstrate that: (1) an equivalent symbolic interpretation is derived describing the overall behaviour of the ANN with high accuracy and fidelity, and (2) a concise explanation is given (in terms of rules, facts and predicates activated in a reasoning episode) as to why a particular instance is being classified into a certain category.

Crosstalk between developmental and tumour-specific signalling pathways : kallikrein-related serine peptidases and nodal in prostrate cancer

Prostate cancer is an important male health issue. The strategies used to diagnose and treat prostate cancer underscore the cell and molecular interactions that promote disease progression. Prostate cancer is histologically defined by increasingly undifferentiated tumour cells and therapeutically targeted by androgen ablation. Even as the normal glandular architecture of the adult prostate is lost, prostate cancer cells remain dependent on the androgen receptor (AR) for growth and survival. This project focused on androgen-regulated gene expression, altered cellular differentiation, and the nexus between these two concepts. The AR controls prostate development, homeostasis and cancer progression by regulating the expression of downstream genes. Kallikrein-related serine peptidases are prominent transcriptional targets of AR in the adult prostate. Kallikrein 3 (KLK3), which is commonly referred to as prostate-specific antigen, is the current serum biomarker for prostate cancer. Other kallikreins are potential adjunct biomarkers. As secreted proteases, kallikreins act through enzyme cascades that may modulate the prostate cancer microenvironment. Both as a panel of biomarkers and cascade of proteases, the roles of kallikreins are interconnected. Yet the expression and regulation of different kallikreins in prostate cancer has not been compared. In this study, a spectrum of prostate cell lines was used to evaluate the expression profile of all 15 members of the kallikrein family. A cluster of genes was co-ordinately expressed in androgenresponsive cell lines. This group of kallikreins included KLK2, 3, 4 and 15, which are located adjacent to one another at the centromeric end of the kallikrein locus. KLK14 was also of interest, because it was ubiquitously expressed among the prostate cell lines. Immunohistochemistry showed that these 5 kallikreins are co-expressed in benign and malignant prostate tissue. The androgen-regulated expression of KLK2 and KLK3 is well-characterised, but has not been compared with other kallikreins. Therefore, KLK2, 3, 4, 14 and 15 expression were all measured in time course and dose response experiments with androgens, AR-antagonist treatments, hormone deprivation experiments and cells transfected with AR siRNA. Collectively, these experiments demonstrated that prostatic kallikreins are specifically and directly regulated by the AR. The data also revealed that kallikrein genes are differentially regulated by androgens; KLK2 and KLK3 were strongly up-regulated, KLK4 and KLK15 were modestly up-regulated, and KLK14 was repressed. Notably, KLK14 is located at the telomeric end of the kallikrein locus, far away from the centromeric cluster of kallikreins that are stimulated by androgens. These results show that the expression of KLK2, 3, 4, 14 and 15 is maintained in prostate cancer, but that these genes exhibit different responses to androgens. This makes the kallikrein locus an ideal model to investigate AR signalling. The increasingly dedifferentiated phenotype of aggressive prostate cancer cells is accompanied by the re-expression of signalling molecules that are usually expressed during embryogenesis and foetal tissue development. The Wnt pathway is one developmental cascade that is reactivated in prostate cancer. The canonical Wnt cascade regulates the intracellular levels of β-catenin, a potent transcriptional co-activator of T-cell factor (TCF) transcription factors. Notably, β-catenin can also bind to the AR and synergistically stimulate androgen-mediated gene expression. This is at the expense of typical Wnt/TCF target genes, because the AR:β-catenin and TCF:β-catenin interactions are mutually exclusive. The effect of β-catenin on kallikrein expression was examined to further investigate the role of β-catenin in prostate cancer. Stable knockdown of β-catenin in LNCaP prostate cancer cells attenuated the androgen-regulated expression of KLK2, 3, 4 and 15, but not KLK14. To test whether KLK14 is instead a TCF:β-catenin target gene, the endogenous levels of β-catenin were increased by inhibiting its degradation. Although KLK14 expression was up-regulated by these treatments, siRNA knockdown of β-catenin demonstrated that this effect was independent of β-catenin. These results show that β-catenin is required for maximal expression of KLK2, 3, 4 and 15, but not KLK14. Developmental cells and tumour cells express a similar repertoire of signalling molecules, which means that these different cell types are responsive to one another. Previous reports have shown that stem cells and foetal tissues can reprogram aggressive cancer cells to less aggressive phenotypes by restoring the balance to developmental signalling pathways that are highly dysregulated in cancer. To investigate this phenomenon in prostate cancer, DU145 and PC-3 prostate cancer cells were cultured on matrices pre-conditioned with human embryonic stem cells (hESCs). Soft agar assays showed that prostate cancer cells exposed to hESC conditioned matrices had reduced clonogenicity compared with cells harvested from control matrices. A recent study demonstrated that this effect was partially due to hESC-derived Lefty, an antagonist of Nodal. A member of the transforming growth factor β (TGFβ) superfamily, Nodal regulates embryogenesis and is re-expressed in cancer. The role of Nodal in prostate cancer has not previously been reported. Therefore, the expression and function of the Nodal signalling pathway in prostate cancer was investigated. Western blots confirmed that Nodal is expressed in DU145 and PC-3 cells. Immunohistochemistry revealed greater expression of Nodal in malignant versus benign glands. Notably, the Nodal inhibitor, Lefty, was not expressed at the mRNA level in any prostate cell lines tested. The Nodal signalling pathway is functionally active in prostate cancer cells. Recombinant Nodal treatments triggered downstream phosphorylation of Smad2 in DU145 and LNCaP cells, and stably-transfected Nodal increased the clonogencity of LNCaP cells. Nodal was also found to modulate AR signalling. Nodal reduced the activity of an androgen-regulated KLK3 promoter construct in luciferase assays and attenuated the endogenous expression of AR target genes including prostatic kallikreins. These results demonstrate that Nodal is a novel example of a developmental signalling molecule that is reexpressed in prostate cancer and may have a functional role in prostate cancer progression. In summary, this project clarifies the role of androgens and changing cellular differentiation in prostate cancer by characterising the expression and function of the downstream genes encoding kallikrein-related serine proteases and Nodal. Furthermore, this study emphasises the similarities between prostate cancer and early development, and the crosstalk between developmental signalling pathways and the AR axis. The outcomes of this project also affirm the utility of the kallikrein locus as a model system to monitor tumour progression and the phenotype of prostate cancer cells.