Construction Workers

Usage case courtesy of: Reza Azodinia, PhD student at the University of Debrecen, Hungary, and Amir Mosavi, Post-Doctoral fellow at UBCO, Canada

 

Click on the picture to see a video

In one of the Alberta's building construction projects a number of workers were surveyed with questionnaires and observations (1). The survey clearly notes the urgent need for training programs to improve their present skill levels. However decision-making on how and with what rate the training programs should be arranged is not a simple task and it has to be considered from different perspectives and criteria. In order to learn how the training programs would affect team efficiencies, team spirit, and team perceptions of supervision, Grapheur (2, 3), the flexible and powerful Business & Engineering Intelligence and Interactive Visualization tool is utilized. With the aid of data mining visualization useful and hidden information are achieved which enhance the multiple criteria decision making in construction industries. The effective decisions are made after clarifying the problem, its dimension, and relation between parameters and objectives.

Data:

More than 150 workers were surveyed with questionnaires and observations. Each row is a construction worker with the corresponding columns, characterized by a series of parameters which are:
  • Name: The ID of each person.
  • Work time: The number of working hours of an employee.
  • Looking for materials: The number of hours an employee has searched for the materials.
  • Looking for tools: The number of hours an employee has searched for a tool.
  • Specialization: Specialization level of an employee.
  • Moving: Moving time of an employee.
  • Instruction: The number of instructions was used by a worker.
  • Idle: The number of hours a worker has been idle.
  • Other characteristics: Other judging criteria of an employee.

Objectives of data mining and visualization:

  • Decision making about the increasing workers' skills
  • To display the condition of each construction worker in the project
  • Sweeping though different characteristic of workers in order to examine the problems carefully
  • Analyzing a particular cluster of workers and their characteristics very carefully; sweeping through skill level and team perception of supervision
  • Providing an effective way to find the best worker of the year

Click on the picture to see a video

Grapheur sample visualization: Similarity Map

1. Decision making about the increasing workers' skills
We are dealing with a series of multiple criteria decision making problems related to construction workers of Canadian construction projects. Here the idea for solving the multiple criteria decision making problems is to visually and effectively model the problems and clarify the whole dimension of them. We use Grapheur, the flexible and powerful business & engineering intelligence and interactive process visualization. It is a smart software for data mining, modeling, problem solving and decision making, newly designed to build models, visualize and optimize them.
For instance we are trying to find out with which rate and how, the workers' level of skills should grow in order to maintain their performance with regard to team perceptions of supervision. For this reason, in order to study a part of the problem, we are considering the similarity map and the parallel filters for optimization the idleness characteristic of the workers. The related multidimensional plot of the networks is created based on the collected data from the workers. The color code represents the specialization of the workers and the size of the bubbles is propor tional to the idleness of workers. In our similarity map of graphical visualization, the gray level of the edges and the generated clusters provide valuable information for decision maker. In the following figure and the provided video the capability of the similarity map in effective clustering the workers into different meaningful clusters is illustrated.
The parallel filters are other useful tools for optimization. The usefulness of parallel filters in reducing the complexity from the process of decision making is evaluated. We start from the matrix of work time in a multidimensional space while aiming at filtering particular workers and examining their performance within the particular group e.g those who have had maximum idleness characteristic.

Click on the picture to see a video

2. To display the condition of each construction worker in the project
For the complete visualization of the condition of each construction worker over all parameters, the colored bubble chart is selected. In the following figure, the colored bubble chart shows work time versus specialization for each worker. The color code and the size of the bubbles represent looking for material characteristic and the idleness status of the workers respectively. Additionally the shape of the bubbles displays the looking for tools characteristic of the workers.
In this graph we have found clustering tool very useful for a deep understanding of the different groups of workers. In this case workers are grouped according to the given characteristics. After grouping, one prototype case for each cluster is visualized which is indeed a very effective way of compressing the information and concentrating on a relevant subset of possibilities.

Click on the picture to see a video

3. Sweeping though different characteristic of workers in order to examine the problems carefully
In the previous graph the relations between work time, specialization, idleness status, looking for materials, and looking for tools characteristics of the construction workers were visualization. Moreover sweeping though data and studying the generated movies is an effective tool for further visualization along with advancing the particular objectives. For instance in our next visualization experience the previous graph is reconsidered by sweeping though looking material, Idleness and skill level as the time advances.

Click on the picture to see a video

4. Analyzing a particular cluster of workers and their characteristics very carefully; sweeping through skill level and team perception of supervision
By sweeping through team perception of supervision and level of specialization of field workers in our building construction project, enhancing the multiple criteria decision making tasks in construction industries is examined in the next graph.
In our bubble graph, the idleness and specialization characteristic of a cluster of four workers is associated with the size and the color of the bubbles relatively. When the skill level of the workers and the team perception of supervision are monthly increased relatively by the rate of 10% and 5% within a year, the idleness characteristic is smoothly monitored. We can also play the resulted animation in smooth mode and track the past values (they appear in a lighter tone in the background of the plot) in order to focus on the changes which occurs according to the morning and afternoon shift.

Click on the picture to see a video

5. Providing an effective way to find the best worker of the year
With the aid of the 7D plot most of the characteristics associated with the best worker comes to our consideration within a single graph. In our case the size, the color and the shape of the bubbles relatively displays the specialization, the moving, and the following the instruction characteristic of the workers. Moreover the blinking feature displays the idleness characteristic of the workers who have been idle less than 100 hours.

Click on the picture to see a video

References:

1 Hewage K.N., Gannoruwa A., Ruwanpura J.Y. (2011), Current Status of Factors Leading to Team Performance of On-Site Construction Professionals in Alberta Building Construction Projects, Canadian Journal of Civil Engineering (in press).
2 Battiti, Roberto; Andrea Passerini (2010). "Brain-Computer Evolutionary Multi-Objective Optimization (BC-EMO): a genetic algorithm adapting to the decision maker." (PDF). IEEE Transactions on Evolutionary Computation 14 (15): 671-687
3 Roberto Battiti and Mauro Brunato, Reactive Business Intelligence. From Data to Models to Insight, Reactive Search Srl, Italy, February 2011.