ERU - 1995
http://dl.lib.uom.lk/handle/123/19483
2024-03-29T14:05:59ZProceedings of Symposium on Industry Related Research 1995 - Pre Text
http://dl.lib.uom.lk/handle/123/19818
Proceedings of Symposium on Industry Related Research 1995 - Pre Text
Dias, WPS
1995-03-01T00:00:00ZHow to introduce new technologies
http://dl.lib.uom.lk/handle/123/19817
How to introduce new technologies
Punchihewa, A
Dias, WPS
1995-03-01T00:00:00ZComputer integration for sri lankan industries - a review
http://dl.lib.uom.lk/handle/123/19816
Computer integration for sri lankan industries - a review
De Silva, S; Wijesoma, WS; De Alwis, AAP
Dias, WPS
production and manufacturing industries employ obsolete methodologies.
However with the advent of personal computers in the early 1980's the user
community enlarged very rapidly. The telecommunication infrastructure has been
enhanced in the last five years allowing private networks such as cellular methodology for
computer interconnectivity.
A good example of optimum use of these facilities is that of local private banks that
open many branches on the Uni Bank principle using centralized host computer directly
connected to the branches as well as ATMs at strategic locations in the city.
Moreover the printing and publishing industry seems to have absorbed new
computer based technology successfully where operations carried out are predominantly
image acquisition, image setting and printing.
This paper is an outcome of an ongoing survey carried out mainly to assess the areas
of application and extent of computerization in the Industrial Sectors in Sri Lanka.
1995-03-01T00:00:00ZArtificial neural networks for construction bid decisions
http://dl.lib.uom.lk/handle/123/19815
Artificial neural networks for construction bid decisions
Dias, WPS; Weerasinghe, RLD
Dias, WPS
An Artificial Neural Network (ANN) approach was explored for supporting construction bid
decisions, since such decisions are heavily dependent on practitioner expertise, which in turn
is generally encapsulated in case histories. One of the ANNs described here was trained on
knowledge from a sample of the entire Sri Lankan construction industry, and was used to
predict the preferred job sizes for firms of differing characteristics; such information could
help firms in their bid/no-bid decisions. The other ANN was trained on case histories elicited
from a single contractor, and was used to predict the percentage mark-up. The network
outputs were obtained in both binary output and continuous valued output formats. The
former format had some distinct advantages over the latter, as it provided greater information
for decision making instead of being a "black box" output. The influences of the middle layer
size, output format and allowable error during training, on the training duration and accuracy
of prediction were studied.
1995-03-01T00:00:00Z