Abstract.A fast algorithm for similarity registration for shapes with various topologies is put forward in this paper. Fourier transform and Geometric moments are explored here to calculate the rotation, scaling and translation parameters to register two shapes by minimizing a dissimilarity measure introduced in the literature. Shapes are represented by signed distance functions. In comparison with the algorithms in the literature, the algorithm proposed here demonstrates superior performance for the registration of two shapes with various topologies as well as two shapes, each containing various and different numbers of shape components. The registration process using this algorithm is robust in comparison with the shape registration algorithms in the literature and is as fast as a couple of FFTs.

We propose a learning method for gait synthesis from a sequence of shapes(frames) with the ability to extrapolate to novel data. It involves the application of PCA, first to reduce the data dimensionality to certain features, and second to model corresponding features derived from the training gait cycles as a Gaussian distribution. This approach transforms a non Gaussian shape deformation problem into a Gaussian one by considering features of entire gait cycles as vectors in a Gaussian space. We show that these features which we formulate as continuous functions can be modeled by PCA. We also use this model to in-between (generate intermediate unknown) shapes in the training cycle. Furthermore, this paper demonstrates that the derived features can be used in the identification of pedestrians.

<p>This paper concerns the development/analysis of the IQ-OTH/NCCD lung cancer dataset. This CT-scan dataset includes more than 1100 images of diagnosed healthy and tumorous chest scans collected in two Iraqi hospitals. A computer system is proposed for detecting lung cancer in the dataset by using image-processing/computer-vision techniques. This includes three preprocessing stages: image enhancement, image segmentation, and feature extraction techniques. Then, support vector machine (SVM) is used at the final stage as a classification technique for identifying the cases on the slides as one of three classes: normal, benign, or malignant. Different SVM kernels and feature extraction techniques are evaluated. The best accuracy achieved by applying this procedure on the new dataset was 89.8876%.</p>

<p class="p1">The use of computer algorithms has gained momentum in filling/assisting roles of specialists especially in early diagnosis scenarios. This paper proposes the employment of deep neural networks (DNN) to detect images with malignant nodules of lung computed tomography (CT). The method includes subjecting input images to a simple and fast pre-processing which isolates regions of interest (ROI), that’s the lungs dominated area, ridding the images of other surrounding tissues and artefacts. Centered and size normalized images are then fed to a deep neural network for training and validation. In this work transfer learning is used to readjust GoogLeNet DNN to learn this medical data. This includes allowing final layers of the DNN to evolve while restricting deep layers. In this setting, a rough, unprocessed dataset, the IQ-OTH/NCCD lung cancer dataset was used to train/validate the proposed algorithm. Experimental results show that this algorithm scores 94.38% accuracy, which outperforms benchmark method previously used with this dataset.</p>

Data-driven soft sensor are inferential models that use on-line available sensor to predict quality variables which cannot be automatically measured at all, or can only be measured at high cost, infrequently, or with high cost and delay (laboratory analysis or on-line analyzer). In soft sensors development, the main issues should deal with treatment varying data, selection of input variables, model training, validation, and soft sensor maintenance to adopt the heavy duty of oil refineries in the aim to improve products and increase yield. In this research improvement on virtual sensor on hybrid soft computing methods fuzzy logic system and neural network which employ to construct the modelling and use rough set theory and differential evolution. This study will work on data of refining of crude oil for two different sources and combine database of them to improve the quality of data discover the knowledge inside the data pattern. The contribution of this study will help to break the barriers of privacy between manufacturers and improve the adoptability of soft sensor modelling to the changes of data sources.