Study Construction Project Assignment Help email Us : email@example.com
Call Us : +44-7497786317
Brunel University, London, Ub7 9fh
Dr. Harris Makatsoris
Abstract- Knowledge Management became the focus of scientific study during the second half of the 20th century. During this time, researchers discovered knowledge resource importance to business organizations. Contrary to early expectations of enhanced management of documents, Management techniques and systems applied in the construction industry fail to deliver the desired performance . Recent research utilizes document content analysis to improve categorization of documents and support retrieval functions. Document text analysis can be performed efficiently using natural language processing. Since project professionals are poor at detecting early warning signs (EWS), identifying the barriers for this cause is critical . Project assessment is useful in identifying EWS associated with the project formalities. This article delivers an unparalleled way to improve the organization of information in organizations and access to inter-organizational systems. The basis is on automated classification of project documents in the construction and in-line with their related project components. Machine learning methods were used for this purpose.
Keywords: Machine learning, early warning signs, Construction project management, unstructured information, Project assessment
The complexity of construction projects makes them prone to failures. Therefore, the introduction of new procurement methods means that many contractors have been forced to rethink their approach to the way risks are treated within their projects and organizations . Project management methodologies can only minimize the risk of failure but cannot guarantee successful completion. However, early prediction of future project trajectory can provide sufficient early warnings and enough time to respond in case significant deviations from the plans are predicted . Such capability requires rapid assessment of project documentation and reports and the ability to infer potential future failures from unstructured information, analysis of emotion and sentiment in the writing style of those reports. Such capability is currently not routinely available.
The research seeks to develop a predictive early warning methodology for project failure prediction by analysing unstructured project documentation such as project reports . Machine learning will be employed to extract from such sources actionable information to compare against project plans and key performance indicators. The research adheres to the developing a project progress assessment methodology encompassing factors affecting project performance. In addition, develop a method and algorithmic approach for the analysis of unstructured project documentation and extraction of key actionable information to allow inference of actual project progress rapidly . The algorithm accompanies the development of a prototype tool tuned against a series of case studies from the literature. Finally it concludes by conducting an empirical study demonstrating the approach.
II. Why construction projects?
The construction industry is characterized by constant changes. As such, document classification requirements and needs becomes paramount. In achieving this classification, consideration issues taken into account include:
- Construction projects are unequalled . Design specification documents contain the plans, formulas, characteristics and implementation plans for construction. The information is both graphic and textual and is communicated to all the stakeholders in the project. Such availability makes construction projects unique. Taking this consideration into account makes an emphasis on these projects relevant to leveraging text mining.
- Dynamic processes are adopted in the construction industry . The design, construction and maintenance is a cycle subject to change over time. There are different concurrent variables that affect the implementation of development projects. Therefore, constant communication must be implemented between the different stakeholders to keep the project phases in sync. The monitoring and tracking poses a challenge which consequently makes construction projects a key area of interest.
- Construction projects are structurally organized . Each structure is assigned a project team composed of contractors, owners, designers and representatives. The independence of the structures makes construction projects an interesting area of study.
- Despite being structurally organized and independent, there is increased collaboration between the projects that involve exchange of information and data to streamline the performance of the system. Through the collaboration, the realization of differences in size and IT capability emerges. The differences act as a foundation for the design of a classification construction management system.
III. Early warning signs
Warning signs are prevalent in construction projects. From definition, they are observational signs that form the basis of proof to the existence of some incipient positive or negative issue . EWS characterize future developments . According to Ansoff’s 1975 , there are two available options to a firm that considers preparing against a strategic weak signal surprise. The first option involves a crisis management strategy . The approach ensures that in the event of weak signal communication detection, the activities of the firm are not negatively influenced to a large extent. The second is a mitigation approach where the problem is pre-determined and mitigated to reduce chances of strategic surprises . Attention must be paid to manage both approach to guarantee their success. According to Loosemore, there are three crisis types in a construction project.
- Creeping crisis- a type of crisis that is just perceive and not addressed until the effect of the crisis occurs
- Sudden crisis- discovered as crisis that occur without prior warning.
- Periodic crisis- they occur in cycles some of which are consistent while others are not.
To curb and minimize the effects of crises, contingency plans should be adopted. Implementing such strategies accompanied by a team of professionally trained project management, the influence and impact of the crisis is drastically reduced .
IV. Unstructured data types
The documents generated and produced in construction projects are essentially unstructured in nature. They are generated in text format since it is the simplest form of communication in this industry . Therefore, access improvement becomes a necessity in these documents. Classification schemes enhance document management, classification and access. Current systems rely on human experts for information extraction. However, the development of systems based on object models and electronic systems enhance structured information storage. Converting unstructured data types increases the ability to retrieve and access information electronically using technology. Unfortunately, the vast majority of construction documents are available as complex unstructured data sources, such as text documents, digital images, web pages, and project schedules. Due to the intricacies of mining and managing this data types, it is less intensively studied although they carry significant and abundant information from construction projects .
V. Text Mining and machine learning
Text documents are the primary exchanges of information adopted in construction projects. The key elements for exchange include, contracts, field reports and orders . Therefore, based on the structure of these documents, management becomes a challenge. Using a model based information extraction system, correlating the data models in the text document also becomes a daunting challenge. On the other hand, a manual approach of establishing connections is impractical due to the high amount of documents stored. The existing systems do not provide room for the required integration. Therefore, an increased need for intelligent, search optimized approach emerges . Despite the availability of such systems, certain limitations are a hindrance to their performance. For example, in cases where words have multiple meanings, and where relevant documents do not contain the user-defined search terms , getting an exact match is a challenge. Text mining becomes vital as it is used to denote all the tasks that involve analysis of large quantities of text documents and tries to extract possibly useful information . The results of the process denote a collection of documents stored in inter organizational systems. They can be used to improve information management and also to generate knowledge about the subjects contained in these documents .
VI. Project Challenges
Some implementation issues taken into account include the following questions:
- What are the most important EWSs of failures specific to project performance in the construction industry? 
- What are the causes of the EWSs specific to projects performance in the construction industry? 
- When is the project performance affected by different factors?
- How to measure datasets; organizational and personal factors?
- VII. Methodology
A mixed methodology approach is used and includes both qualitative and quantitative methods. Specifically, a mixture of data from both the literature and real life is employed to demonstrate this approach . A news consolidation system is used as the point of focus as it provides a realistic scenario where data captured is textually mined and correlated with the algorithms of data mining and machine learning. The essence of using such an approach is to correlate early warning signs that characterize construction projects with text mining approaches. Once information is acquired inform of raw data, it undergoes different processing forms to be delivered to the user in the manner in which they searched for the information. As was previously stipulated in this research, construction projects are characterized by complexity especially in the data acquisition and management processes. Identification of early warning signs in the acquired data may indicate the clarity of the data, and whether it is exact or inexact or in other cases whether any signal has been received. Taking this approach and applying it in a construction project, it can be determined whether the acquired information requires further analysis of textual mining or the received information enhances the development and management of resources in the construction project . The project described in this paper used data from construction inter-organizational information systems to evaluate text classification algorithms and to guide the development of the prototype of building a document classification system. The real life application scenario use as a methodology impacts on the credibility and authenticity of the report. Therefore, the project is divided into phases, and each one of these stages has objectives.
A. Analytical Phase:
The phase captures the early warnings of the project failures that occur in construction projects . The beginning of the warnings and parameters defined in each of its related papers is tabulated as shown and recorded (TABLE 1).
table 1 A primary list of early warnings and a description of issues analyzed and referenced from different sources.
|Early Warnings||Early Warnings Issue||References|
|Lack of making purchases||The style of delays to make purchases ||EWS, Ilmari O. Nikander, 2000 |
|Lack of materials on site||shortage of materials delaying the work|
|Lack of resources ||Shortage of staff, poor mix of responsibility||Kappelman et IT projects 2006 |
|Lack of keen commitment to the project milestone and scopes||Delivering the promised project scope (e.g. freezing action, repetitive action) ||Kappelman et IT projects 2006 |
|Lack of project team required knowledge/skills||Uncertainty regarding technical matters indicates ignorance||McKeeman, 2001|
Figure 1: A high level overview of the system.
B. Model Phase:
Like any other model, a practical approach is implemented through modelling. The management system will be developed to read the data from unstructured documents and to detect the early warnings that are affect or could influence the undergoing construction project .
The Text Mining technique will be used to represent all the tasks that, try to extract possibly useful information . Results of the text mining process will be a collection of generic attributes that store information about a particular item.The unstructured document that can be assisted by a classifier to generate knowledge about the subjects contained in these documents.
Naïve Bayes classification (Equations 1, 2) will be employed automatically to build a classifier that will interpret the class/category where the object belongs. First, equation (1) will be applied to calculate the probability of new entities by observing the features of a set of documents that have previously been classified manually into the approach training set . Hence, this approach relies on the existence of an initial corpus of early warnings, previously classified according to their relevance to a particular task in the project plan . Next, equation (2) will be applied to determine the probable threat or warnings that arise from parsing the item text.
Finally, an effectiveness evaluation will be applied by splitting the initial collection of documents into two sets. Training set phase that will be used to create the approach model and the Test set phase that will be used for testing the strategy model .
- : The training set step algorithm has been used especially to calculate the probability of new entities from unstructured documents .
Where P (Wk|h) is the probability of observing data. Wk gives some attributes where approach early warnings holds (H), n is how many times there are object occurrences in the approach trying set, (nk) is number of times the observed data occurred in the category of the approach training set, |Vocabulary| is a unique attributes dictionary that has been identified according to its value to the subject.
Second: Naïve Bayes probabilistic with strong assumptions used to build the classifier .
hMAP refers to the maximum probability of early warnings. P (D|H) is the likelihood of the observed data given the approach of early warnings, and (pH) is the probability of the approaching first signs.
VIII. Early Warning Signs architecture
The architecture of EWS consists of three principal components (as shown in Figure 2):
- Input (Data gathering sources)
- News consolidation system
- Bright and dark Web analysis
- Data gathered manually from fields
- Semantic entity and relationship management system. Through semantics, also known as rules of classification, Information relevant to early warnings may be characterized as knowledge. The obtained knowledge is about things, activities and conditions. The information about things represents attributes of the actors and is typically presented as profiles.
- Social network analysis (SNA) tools
- Interface for social scientists to create and manage rules and interact with each other’s theories
- Interface for social scientists to analyse data.
- Rule based engine
- Warning generation Engine
- Notification system
A notification system is needed to send to the warnings subscriber devices, which have subscribed themselves against warning(s) or rule-based theories. The notification system should be capable of managing subscription information and subscriber devices. Ideally speaking, we should be able to interface any device with our notification system. A realist approach would be that we have to take care of at least two devices: email receiver (an internet enabled machine) and SMS receiver (a mobile phone).
Figure 2: EWAS System Architecture
In order to have a logical outcome we still need to develop the approach to the trying set, based on the existence of early warnings signs along with specific tasks in the project plan. These expected results from the system can allow construction projects to be assessed routinely and more promptly.
Project performance indicators fail to provide valuable, and relevant information as the measures are lagging indicators . EWS focus on providing leading indicators. Process and people related risks score high than product risks in an IT project failure. Complexity influences the ability to identify and respond to early warning signs. As previously outlined, construction projects are characterized by complexity . Risks and uncertainty in projects results from unambiguous goals. Analyzing and understanding outputs and behaviors from inputs is difficult to assess the complexity of a system. Since project assessment is a full concept, it comprises of different appraisals to support decision-making. The main types of project assessments are provided in Table 2
In the building and construction industry, there are numerous ways of extracting data . However, the best approach clearly captures the sources of the information signal in an effort of ensuring that clear and exact information is included in the analysis. Information prediction can be done from three methods which are neural networks, support vector regression and decision trees. The naïve Bayes classification model depicted in Figure 3 calculates the EWS through 166 training logs. The higher the testing variables, the more concise the final output is determined. Therefore, the classification criteria depends on the level and type of signal from the EWS detection system . The initial results from the Bayes’ classifier determines whether the text and data mining process was a success or a failure. The ability to project the exact results means that the developed algorithm meets the input data and all searches are satisfied.
Figure 3: initial result of the system
According to previous results, the measurements of project success are essential for project control in an effort of achieving project objectives. Fixed factors and inference methods with few challenges was used and proved to be inadequate in this models . A predictor analysis model deployed indicated the results shown below.Figure 4: Predictor analysis of owner expenditures adapted from Russell et al. 1997
A list of initial early warnings has been collected to reveal the approach of the trying set (Corpus). The research background information on why construction projects are a useful resource for text and data mining extraction is provided. To achieve this, an algorithm based on Naïve Bayes has been successfully applied to calculate the probability of early warning signs for the first time . It appears to be a reasonable result so far. However, as mentioned in the results above, further development into the approach of the trying set is still needed in order to accomplish predictions, as well as comparisons. Developing a classification algorithm that captures the needs of the construction industry is still a prevalent challenge. The uniqueness and complexity of the information in the industry is what makes it a challenge. There is still room for improvement to ensure that the complexity of the data available in the construction industry is properly analyzed, determined and predicted to meet the search criteria of all the stakeholders involved. The project can potentially have a significant impact on the construction industry globally by;
- Establishing a unique methodology in project performance/failure prediction.
- It’s a rapid performance analysis early warning system leveraging the wealth of information that is currently in unstructured formats and therefore not actionable by conventional software project management systems . The research is still at year 3 of a Ph.D. program, but rapid progress is anticipated.
XI. FUTURE PLAN/ DIRECTIONS
The construction industry is still in its infancy in the area of data mining and analysis . To achieve detailed analysis and results, this paper proposes adoption of an empirical study. The approach should consider selection of construction projects as case studies for the achievement of this purpose. Comparing more than one construction project will enable the determination of how early warning parameters affect the project plan. In addition to this, to predict the project performance, all the phases of a construction project are observed. Monitoring a project for a particular period achieves this parameter. Rapid progress is anticipated in machine learning and specifically textual data analysis in the construction industry. An inherent reduction in the complexity of the construction projects will be achieved. .
- Andersen, O.M. Magnussen Identifying and acting on early warning signs in complex projects Project Management Journal, 43 (2012), pp. 37–53
- Ansoff, H. I. (1975). Managing strategic surprise by response to weak signals.California Management Review, 21–33
- Q. Mohanned, K. Amr
Concept relation extraction from construction documents using natural language processing
Journal of Construction Engineering Management, Vol. 136 (3) (2010), pp. 294–302
- Archer, G. O., Futcher, K., and McMahon, M. A. (1994). “Multi participant project information management system.” Centre for Construct IT, University of Hong Kong (accessed from ^http:// hkusury2.hku.hk/ConstIT/R3pims.html&).
- Kosovac, T. Froese, D. Vanier, Integration heterogeneous data representations in model-based AEC/FM systems, in: Proc. of CIT 2000, Reykjavik, Iceland
- H. Caldas, L. Soibelman, L. Gasser, Methodology for the integration of project documents in model-based information systems, Journal of Computing in Civil Engineering (2005)
- H. Caldas, L. Soibelman, (2003). “Automated Classification of Construction Project Documents”, Automation in Construction, 12, pp. 395–406.
- J . H. M. TAH & V. CARR Information modelling for a construction project risk management system Project Systems Engineering Research Unit, School of Construction, South Bank University, Wandsworth Road, London SW8 2JZ, UK
- Soibelman, M.ASCE, H. Kim, (2002). “Data preparation process for construction knowledge generation through Knowledge Discovery in Databases”, Journal of Computing in Civil Engineering, 16 (1), pp. 39–48
- Kappelman, LA, and R McKeeman,(2006). “Early Warning Signs of it Project Failure.” The EDP Audit, Control, and Security Newsletter (EDPACS), P. 3-4.
- Kappelman, L. A.,McKee man, R., &Zhang, L. (2006) Early warning signs ofIT project failure: The dominant dozen. Information Management Systems, 23(4), 31–36
- Soibelman, H. Kim, Data preparation process for construction knowledge
generation through knowledge discovery in databases, Journal of
Computing in Civil Engineering (January 2002) 39–48
- Soibelman, J. Wu, C. Caldas, I. Brilakis, K.Y. Lin Management and analysis of unstructured construction data types Advanced Engineering Informatics, 22 (1) (2008), pp. 15–27
- Loosemore, M. (1999). A grounded theory of construction crisis management. Construction Management &
- McKee man, R, (2001). “Early Warning Signs of Project Failure”, Report for University of North Texas
- Memon, N., Wiil, U. K., and Qureshi, A. R., “Design and Development of an Early Warning System to Prevent Terrorist Attacks, ” Proceedings of the International Conference on Artificial Intelligence and Neural Networks, pp.222-226, 2009
- Nikander, I. O., & Eloranta, E, (2001).“Project Management By Early Warnings”, International Journal of Project Management, 19, 385–399.
- Nikander, I. O., & Eloranta, E,(2002). “Early Warnings: A phenomenon in project management”, Dissertation for Doctor of Science in Technology, Helsinki University of Technology, Espoo, Finland.
- Ur-Rahman, N. & Harding, J.A. (2012). Textual data mining for industrial knowledge management and text classification: A business oriented approach. Expert Systems with Applications, 39, 4729- 4739. doi:10.1016/j.eswa.2011.09.124
- Vidogah, W., and Ndekugri, I. 1998a. “Improving the management of claims on construction contracts: Consultant’s perspective.” Constr. Manage. Econom., 163, 363–372
- Mao, Y. Zhu, I. Ahmad Applying metadata models to unstructured content of construction documents: a view-based approachAutomation in Construction, 16 (2007), pp. 242–252
- Williams, T., Klakegg, O. J., Walker, D. H. T., Andersen, B. and; Magnussen. O. M.(2012) “Identifying and Acting on Early Warning Signs in Complex Projects”, Project Management Journal, 43:2, April, pp. 37–53.
- Williams et al., 2012 T.M. Williams, O.J. Klakegg, D.H.T. Walker, B.