Kartläggning av plastkorkar och förslag till förbättringar för den australiensiska marknaden

The project Design analysis and proposals of plastic screw caps in Australia was performed at Högskolan Dalarna incooperation with University of Western Sydney, Australia. The Swedish company Tetra Pak, in Lund, were assigner forthe project that was performed 2006-2007. The commission was to do a survey about the packages for non-carbonateddrinks in Australia. The bottles had to be plastic, able to open in one step and with focus on the caps.The project has result in design analysis and a new proposal of a plastic screw cap for the Australian market. Sixbottles were choosen and they were all testet on 20 consumers each with a Likert-scale test. The result from the test andthe survey underlied the work with a proposal of a new design. The most important qualities for a optimal opening is:a tamper that is easy to break and also guarantee that is not been opened before, wide and soft grip, ergonomics, easyto close and that is good looking.

Feasible estimation of generalized linear mixed models (GLMM) with weak dependency between groups

This paper presents a two-step pseudo likelihood estimation technique for generalized linear mixed models with the random effects being correlated between groups. The core idea is to deal with the intractable integrals in the likelihood function by multivariate Taylor's approximation. The accuracy of the estimation technique is assessed in a Monte-Carlo study. An application of it with a binary response variable is presented using a real data set on credit defaults from two Swedish banks. Thanks to the use of two-step estimation technique, the proposed algorithm outperforms conventional pseudo likelihood algorithms in terms of computational time.

Portals for microenterprises in rural area : two cases

Research has shown that microenterprises have ability to survive and grow with the support of portals that include eCcommerce. However, almost no research has demonstrated how it’s done and what support microenterprises want. Results of our study shows that the portals have to be improved to support the use of advanced ICT applications, make it usable to use, and give more time for core business for the participating microenterprises. We have seen that portals have to solve problem with the technical solution and the process of payment. The network building activities in the portals do not happen in such extent that we have expected based on previous research. If portals will get businesses to grow in microenterprises, we propose that in addition to providing access to advanced ICT applications need to climbs one step higher in the DTI ladder and create more of eCommerce to increase sales in a greater market. We also propose that portals which support cooperation between microenterprises in rural areas from different branches have the best chances to succeed in the future.

Speed prediction for triggering vehicle activated signs

Accurate speed prediction is a crucial step in the development of a dynamic vehcile activated sign (VAS). A previous study showed that the optimal trigger speed of such signs will need to be pre-determined according to the nature of the site and to the traffic conditions. The objective of this paper is to find an accurate predictive model based on historical traffic speed data to derive the optimal trigger speed for such signs. Adaptive neuro fuzzy (ANFIS), classification and regression tree (CART) and random forest (RF) were developed to predict one step ahead speed during all times of the day. The developed models were evaluated and compared to the results obtained from artificial neural network (ANN), multiple linear regression (MLR) and naïve prediction using traffic speed data collected at four sites located in Sweden. The data were aggregated into two periods, a short term period (5-min) and a long term period (1-hour). The results of this study showed that using RF is a promising method for predicting mean speed in the two proposed periods.. It is concluded that in terms of performance and computational complexity, a simplistic input features to the predicitive model gave a marked increase in the response time of the model whilse still delivering a low prediction error.