Deep-hole drilling process, monitoring system and sensors modifications

 In the drilling processes and especially deep-hole drilling process, the monitoring system and having control on mechanical parameters (e.g. Force, Torque,Vibration and Acoustic emission) are essential. The main focus of this thesis work is to study the characteristics of deep-hole drilling process, and optimize the monitoring system for controlling the process. The vibration is considered as a major defect area of the deep-hole drilling process which often leads to breakage of the drill, therefore by vibration analysis and optimizing the workpiecefixture, this area is studied by finite element method and the suggestions are explained. By study on a present monitoring system, and searching on the new sensor products, the modifications and recommendations are suggested for optimize the present monitoring system for excellent performance in deep-hole drilling process research and measurements.

Extending the Hydra Head to Create a Pluggable, Extensible Architecture: Diving into the Technology of Hydramata

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

Fedora 4.0 Deep Dive

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

Deep generative models for facial keypoints detection

A new area of machine learning research called deep learning, has moved machine learning closer to one of its original goals: artificial intelligence and general learning algorithm. The key idea is to pretrain models in completely unsupervised way and finally they can be fine-tuned for the task at hand using supervised learning. In this thesis, a general introduction to deep learning models and algorithms are given and these methods are applied to facial keypoints detection. The task is to predict the positions of 15 keypoints on grayscale face images. Each predicted keypoint is specified by an (x,y) real-valued pair in the space of pixel indices. In experiments, we pretrained deep belief networks (DBN) and finally performed a discriminative fine-tuning. We varied the depth and size of an architecture. We tested both deterministic and sampled hidden activations and the effect of additional unlabeled data on pretraining. The experimental results show that our model provides better results than publicly available benchmarks for the dataset.