Person Re-Identification using Deep Convnets with Multi-task Learning

Person re-identification involves recognizing a person across non-overlapping camera views, with different pose, illumination, and camera characteristics. We propose to tackle this problem by training a deep convolutional network to represent a person’s appearance as a low-dimensional feature vector that is invariant to common appearance variations encountered in the re-identification problem. Specifically, a Siamese-network architecture is used to train a feature extraction network using pairs of similar and dissimilar images. We show that use of a novel multi-task learning objective is crucial for regularizing the network parameters in order to prevent over-fitting due to the small size the training dataset. We complement the verification task, which is at the heart of re-identification, by training the network to jointly perform verification, identification, and to recognise attributes related to the clothing and pose of the person in each image. Additionally, we show that our proposed approach performs well even in the challenging cross-dataset scenario, which may better reflect real-world expected performance. 

A Non-catalytic Deep Desulphurization Process using Hydrodynamic Cavitation

A novel approach is developed for desulphurization of fuels or organics without use of catalyst. In this process, organic and aqueous phases are mixed in a predefined manner under ambient conditions and passed through a cavitating device. Vapor cavities formed in the cavitating device are then collapsed which generate (in-situ) oxidizing species which react with the sulphur moiety resulting in the removal of sulphur from the organic phase. In this work, vortex diode was used as a cavitating device. Three organic solvents (n-octane, toluene and n-octanol) containing known amount of a model sulphur compound (thiophene) up to initial concentrations of 500 ppm were used to verify the proposed method. A very high removal of sulphur content to the extent of 100% was demonstrated. The nature of organic phase and the ratio of aqueous to organic phase were found to be the most important process parameters. The results were also verified and substantiated using commercial diesel as a solvent. The developed process has great potential for deep of various organics, in general, and for transportation fuels, in particular.

Proposing the deep dynamic Bayesian network as a future computer based medical system

The development of new learning models has been of great importance throughout recent years, with a focus on creating advances in the area of deep learning. Deep learning was first noted in 2006, and has since become a major area of research in a number of disciplines. This paper will delve into the area of deep learning to present its current limitations and provide a new idea for a fully integrated deep and dynamic probabilistic system. The new model will be applicable to a vast number of areas initially focusing on applications into medical image analysis with an overall goal of utilising this approach for prediction purposes in computer based medical systems.