THE CSI JOURNAL ON COMPUTER SCIENCE AND ENGINEERING
Year:2003 | Volume:1 | Issue:3 (a)|Papers Count:5

During the last decade molecular genetics has gone through great transformation. One of these changes has been the advent of Microarray technology. Microarray is a powerful tool for analysis" and study of thousands of genes simultaneously. A bottleneck in this technology is the time that is required to process the produced images. This part is currently done by software routines. In this paper, a pipeline architecture is presented for processing, compression and transmission of Microarray images. The suggested design is completely modular and expandable and hence, it is suitable for implementation by VLSI standard cells techniques. The complexity of the hardware is only a function of the width of images and not their lengths. The required time for processing, compression and transmission of a 256x256 image is in order of milliseconds.

In this paper, a novel probability distribution representation method has been proposed for acoustic speech segments. This representation is applicable to various acoustic models. In this method, the probability density of each feature vector is calculated by a selected Gaussian distribution, which is compatible with environmental conditions. This Gaussian distribution is selected among pre-estimated Gaussian clusters of each phoneme. In this regard, the required training and recognition algorithms are developed and analyzed in this paper. It is shown that the training time is reduced drastically while the recognition rate has remained unchanged. In addition, the GVQ method makes an appropriate analytical framework for Gaussian selection approaches to speed up the recognition phase.

Improving testability during the early stages of High-level Synthesis (HLS) has several benefits including reduced test hardwar, overheads, reduced test costs, reduced design iterations, and significant improved fault coverage. In this paper, we present a novel register allocation algorithm which is based on weighted graph coloring, targeting testability improvement. In our register allocation method, several high-level testability parameters including sequential depth, sequential loop, and controllability/observability are considered. Experiments show using this register allocation method results in significant improvement in A TPG time and fault coverage.

Tracking moving objects in an image sequence is one of the important topics in computer vision. The huge volume of investigations carried out by researchers in recent decades in this field, and the different methods developed to solve this problem in different applications are witnesses to this claim. Because of the wide range of techniques involved and the variety of proposed solutions, it is not easy to master the background and begin a research in this field. Presentation of the issues arising in this area and reviewing the related research work can help the new researchers of the field and facilitate their work. This paper discusses the general issues involved in object tracking, and presents the over view of literature existing in this field in the form of a useful classification. Also, the parameters influencing an object-tracking system and the features of an ideal object-tracking system are discussed. In addition, Different applications of object-tracking systems are also introduced in the course of the discussions.