Oerip S. Santoso

Color retinal image enhancement using CLAHE

Common method in image enhancement thats often use is histogram equalization, due to this method is simple and has low computation load. In this research, we use Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance the color retinal image. To reduce this noise effect in color retinal image due to the acquisition process, we need to enhance this image. Color retinal image has unique characteristic than other image, that is, this image has important in green (G) channel. Image enhancement has important contribution in ophthalmology. In this paper, we propose new enhancement method using CLAHE in G channel to improve the color retinal image quality. The enhancement process conduct in G channel is appropriate to enhance the color retinal image quality.

Generic data model patterns using Fully Communication Oriented Information Modeling (FCO-IM)

In the specific area of data modeling, data model patterns have been introduced and used to help creating highquality conceptual data models. Generic data model patterns, in particular, are expected to be more useful in helping to solve more data modeling problems in comparison to domain-specific patterns. A collection of generic patterns using Fully Communication Oriented Information Modeling (FCO-IM) as the modeling approach is described in this paper. They can generally be divided into two categories: (1) Patterns that are based on the identification of an object, consist of 5 patterns; (2) Patterns that are based on the relation between two objects, consist of 6 patterns. The generic patterns are needed to be documented in full details and then to be shared in wider audience to have comments and improvements.

Designing Artificial Immune System Based on Clonal Selection: Using Agent-Based Modeling Approach

Bio-inspired computing is the idea to emulate and to get inspirations from biological systems which is then used to solve complex problems. Artificial immune systems, as one of the bio-inspired computing has contributed in solving complex problems. From one generation to another generation, AISs practitioners realize that to get better algorithms we need the inspiration with the better understanding about the behavior of the immune system. Modeling is the key to get better understanding and inspiration from immune system. Agent-based modeling can be used because of the components of the immune system can be described as agents that interact with each other and set up a system behavior. There are two approaches to agent-based modeling, i.e. modeling of the immune system itself and model the artificial immune system. In this paper we design a model for immune system using agent-based approach. This model specifically based on clonal selection and its behavior. The design of model are using UML diagram to describe the behavior and the interaction of agents. This design can be used for simulating existing artificial immune system models, developing new artificial immune system models, or evaluating artificial immune system models that have been already adapted to technical problems.

Detection of cerebral aneurysms by using time based parametric color coded of cerebral angiogram

Cerebral aneurysm is a cerebrovascular disorder in which weakening in the walls of brain blood vessels causing a swelling or dilation of blood vessels. The disease is also called intracranial aneurysms and usually occurs around the arteries at the base of the brain called the Circle of Willis.

Detection method of cerebral aneurysm based on curvature analysis from 3D medical images

Cerebral aneurysm is a weak spot in a blood vessel that usually enlarges. Nowadays, cerebral aneurysm detection method is still being done manually by visually observing 2D or 3D medical images (CTA). The main purpose of this paper is to design a method of cerebral aneurysm detection and classify different vascular geometry with color indicator. The method developed was based on curvature analysis of wall vasculatures model that were reconstructed from 3D CTA images. The curvature shape index defined as I=(K1+K2)/K1 where K1 and K2 are the main curvature of vascular model then used as the base of vascular coloring system. Results showed that the shape index is able to differentiate different parts of vasculature model and detect the present of an aneurysm.

Role of pressure and wall shear stress in initiation and development of cerebral aneurysms

Cerebral aneurysm is a cerebrovascular disorder in which weakness in the wall of a cerebral artery or vein causes a localized dilation or ballooning of the blood vessel. Other studies demonstrated that hemodynamic plays important role in the initiation and development of cerebral aneurysm. Wall shear stress and pressure are among the hemodynamic factors that contribute to the initiation and development of the cerebral aneurysm. In this study, the distribution of wall shear stress and pressure around cerebral aneurysms and its pre-aneurysms state were analyzed using the method of computational fluid dynamics.

Information grammar for patterns (IG P ) for pattern language of data model patterns based on fully communication oriented information modeling (FCO-IM)

The use of patterns in a design process, including data modeling, is an attempt to create a better solution to a problem. We propose the use of data model patterns, organized in a pattern language, and based on Fully Communication Oriented Information Modeling (FCO-IM) as the modeling approach, as a standard to produce high quality data models. We introduce the concept of Information Grammar for Pattern (IGP) which works as a kind of template to generate FCOIMs Information Grammar (IG). IGP is also used to define the relations among patterns. Based on how they are abstracted, we also define 3 types of IGP. The IGP provides the basic idea for the pattern language of data model patterns based on the relations among patterns.

Performance Evaluation of Color Retinal Image Quality Assessment in Asymmetric Channel VQ Coding

The RGB color retinal image has an interesting characteristic, i.e. the G channel contains more important information than the other ones. One of the most important features in a retinal image is the retinal blood vessel structure. Many diseases can be diagnosed based on in the retinal blood vessel, such as micro aneurysms that can lead to blindness. In the G channel, the contrast between retinal blood vessel and its background is significantly high. The authors explore this retinal image characteristic to construct a more suitable image coding system. The coding processes are conduct in three schemes: weighted R channel, weighted G channel, and weighted B channel coding. Their hypothesis is that allocating more bits in the G channel will improve the coding performance. The authors seek for image quality assessment (IQA) metrics that can be used to measure the distortion in retinal image coding. Three different metrics, namely Peak Signal to Noise Ratio (PSNR), Structure Similarity (SSIM), and Visual Information Fidelity (VIF) are compared as objective assessment in image coding and to show quantitatively that G channel has more important role compared to the other ones. The authors use Vector Quantization (VQ) as image coding method due to its simplicity and low-complexity than the other methods. Experiments with actual retinal image shows that the minimum value of SSIM and VIF required in this coding scheme is 0.9940 and 0.8637.

Using unified modeling language to model the immune system in object oriented perspective

Artificial Immune System (AIS) has become known as an area of computer science and engineering that uses immune systems metaphors to solve problems with a novel solution. The immune system has an interesting area for computer scientists with its uniqueness and fascinating computational system that has evolved to solve a unique problem. A deeper understanding of the immune system, in part through the use of modeling techniques, which will lead to the development of richer, more effective immune inspired engineered systems. It can suggest new solutions to computer science problems, or at least give us new ways of looking at these problems. This paper shows that bio-systems like immune system can be modeled using the object oriented perspective. We use Unified Modeling Language to represent the behavior of immune system and the interaction between immune system elements. The introduction motivates the need of immune system modeling at different levels of abstraction. Then the UML diagrams are used to illustrate the static and the dynamic behavior of immune system. There are an examples model for elementary clonal selection that involved B-cell, antibodies, and antigen correspondences. Since there are 14 (fourteen) diagrams of UML, this paper uses some of the diagrams. There are the use-case diagram to show functionality of immune system, activity diagrams to show the global abstractions of system and the class diagram to show the structure of immune system elements. At the conclusion, we can see that OO perspectives are promising the better understanding for complex bio-systems such as immune system. This is lead to get the better bio-inspired computation solutions to solve computer science problems.

Multi-Inductive Learning approach for Information Extraction

The vast amount of information in the Internet is not easy to find and use. Information Extraction technology is one of alternatives that can solve this problem. Conventional Natural Language Processing approach is hampered by its portability, scalability and adaptability. Introduction of Machine Learning into Information Extraction is one of solutions. Inductive Learning only needs annotated training examples. The problem is there is no performance consistency of algorithms on various information domains. Automatic and smart classifier selection from various machine learning algorithms is one of the best way to handle this problem. The goal of this paper is to propose a method for Information Extraction System based on Inductive Learning and Meta Learning that have good performance. In this paper Multi-Inductive Learning is developed to answer that question. Multi-Inductive Learning is consist of several Inductive Learning algorithms that have significant difference in their mechanism. This is to ensure there is bias variance in this method. Through k-fold cross validation on training document, Multi-Inductive Learning algorithm can choose the best classifier for each slot on a certain domain. These best classifiers then employ to do full extraction on testing document. The conducted experiment shows that Multi-Inductive Learning has better performance than that of single Inductive Learning algorithm-based Information Extraction systems. On Reuters Corporate Acquisition, Multi-Inductive Learning gives a score of 46.3 % and has the best performance among other state of the art information systems. Out of nine slots that should be extracted, six of them give the best performance. Multi-Inductive Learning also gives better performance on Job Posting dataset. Average performance of it gives 82.1 % and is the best among other state of the art of Information Extraction. Out of 17 slots that should be tested, nine of them are extracted with the best performance.