A neural network based tool for semi-automatic code transformation

A neural network based tool has been developed to assist in the process of code transformation. The tool offers advice on appropriate transformations within a knowledge-driven, semi-automatic parallelisation environment. We have identified the essential characteristics of codes relevant to loop transformations. A Kohonen network is used to discover structure in the characterised codes thus revealing new knowledge that may be brought to bear on the mapping between codes and transformations or transformation sequences. A transform selector based on this process has been developed and successfully applied to the parallelisation of sequential codes.

A comparison between randomly alternating imaging, normal laparoscopic imaging, and virtual reality training in laparoscopic psychomotor skill acquisition

Objectives: To evaluate virtual reality as a laparoscopic training device in helping surgeons to automate to the “fulcrum effect” by comparing it to time-matched training programs using randomly alternating images (ie, y-axis inverted and normal laparoscopic) and normal laparoscopic viewing conditions.

Methods: Twenty-four participants (16 females and 8 males), were randomly assigned to minimally invasive surgery virtual reality (MIST VR), randomly alternating (between y-axis inverted and normal laparoscopic images), and normal laparoscopic imaging condition. Participants were requested to perform a 2-minute laparoscopic cutting task before and after training.

Results: In the test trial participants who trained on the MIST VR performed significantly better than those in the normal laparoscopic and randomly alternating imaging conditions.

Conclusion: The results show that virtual reality training may provide faster skill acquisition with particular reference to automation of the fulcrum effect. MIST VR provides a new way of training laparoscopic psychomotor surgical skills.

A machine vision approach to the grading of crushed aggregate

The grading of crushed aggregate is carried out usually by sieving. We describe a new image-based approach to the automatic grading of such materials. The operational problem addressed is where the camera is located directly over a conveyor belt. Our approach characterizes the information content of each image, taking into account relative variation in the pixel data, and resolution scale. In feature space, we find very good class separation using a multidimensional linear classifier. The innovation in this work includes (i) introducing an effective image-based approach into this application area, and (ii) our supervised classification using wavelet entropy-based features.