In this paper we describe CB513 a non-redundant dataset, suitable for development of algorithms for prediction of secondary protein structure. A program was made in Borland Delphi for transforming data from our dataset to make it suitable for learning of neural network for prediction of secondary protein structure implemented in MATLAB Neural-Network Toolbox. Learning (training and testing) of neural network is researched with different sizes of windows, different number of neurons in the hidden layer and different number of training epochs, while using dataset CB513.

The purpose of this study is to model and optimize the detection of tar in cigarettes during the manufacturing process and show that low yield cigarettes contain similar levels of nicotine as compared to high yield cigarettes while B (Benzene), T(toluene) and X (xylene) (BTX) levels increase with increasing tar yields. A neuro-fuzzy system which comprises a fuzzy inference structure is used to model such a system. Given a training set of samples, the Adaptive Neuro-Fuzzy Inference System (ANFIS) classifiers learned how to differentiate a new case in the domain. The ANFIS classifiers were used to detect the tar in smoke condensate when five basic features defining cigarette classes indications were used as inputs. A classical method by High Performance Liquid Chromatography (HPLC) is also introduced to solve this problem. At last the performances of these two methods are compared.

The paper presents the implementation of Object-Oriented (OO) integrated approaches to the design of scalable Electro-Cardio-Graph (ECG) Systems. The purpose of this methodology is to preserve real-world structure and relations with the aim to minimize the information loss during the process of modeling, especially for Real-Time (RT) systems. We report on a case study of the design that uses the integration of OO and RT methods and the Unified Modeling Language (UML) standard notation. OO methods identify objects in the real-world domain and use them as fundamental building blocks for the software system. The gained experience based on the strongly defined semantics of the object model is discussed and related problems are analyzed.

For medical volume visualization, one of the most important tasks is to reveal clinically relevant details from the 3D scan (CT, MRI ...), e.g. the coronary arteries, without obscuring them with less significant parts. These volume datasets contain different materials which are difficult to extract and visualize with 1D transfer functions based solely on the attenuation coefficient. Multi-dimensional transfer functions allow a much more precise classification of data which makes it easier to separate different surfaces from each other. Unfortunately, setting up multi-dimensional transfer functions can become a fairly complex task, generally accomplished by trial and error. This paper explains neural networks, and then presents an efficient way to speed up visualization process by semi-automatic transfer function generation. We describe how to use neural networks to detect distinctive features shown in the 2D histogram of the volume data and how to use this information for data classification.