Papers by deepa saibannavar
Malaria is a serious global health problem, and rapid, accurate diagnosis is required to control ... more Malaria is a serious global health problem, and rapid, accurate diagnosis is required to control the disease. An image processing algorithm to automate the diagnosis of malaria in blood images is developed in this paper. The image classification system is designed to positively identify malaria parasites present in thin blood smears, and differentiate the species of malaria. The implemented new approach to low-level image processing -SUSAN (Smallest Univalue Segment assimilating Nucleus) Principle, performs Edge and Corner Detection. Images are acquired using a charge-coupled device camera connected to a light microscope. Morphological and novel threshold selection techniques are used to identify erythrocytes (red blood cells) and possible parasites present on microscopic slides. Image features based on colour, texture and the geometry of the cells and parasites are generated, as well as features that make use of a priori knowledge of the classification problem and mimic features us...
Malaria is a serious global health problem, and rapid, accurate diagnosis is required to control ... more Malaria is a serious global health problem, and rapid, accurate diagnosis is required to control the disease. An image processing algorithm to automate the diagnosis of malaria in blood images is developed in this paper. The image classification system is designed to positively identify malaria parasites present in thin blood smears, and differentiate the species of malaria. The implemented new approach to low-level image processing-SUSAN (Smallest Univalue Segment assimilating Nucleus) Principle, performs Edge and Corner Detection. Images are acquired using a charge-coupled device camera connected to a light microscope. Morphological and novel threshold selection techniques are used to identify erythrocytes (red blood cells) and possible parasites present on microscopic slides. Image features based on colour, texture and the geometry of the cells and parasites are generated, as well as features that make use of a priori knowledge of the classification problem and mimic features used by human technicians. The first order features provides the basic mathematical ranges for different types of parasites. A two-stage tree classifier distinguishes between true and false positives, and then diagnoses the species of the infection. Malaria samples obtained from the various biomedical research facilities are used for training and testing of the system.
Vehicular Ad-hoc Networks (VANET'S) have become viable and valuable for their wide variety of nov... more Vehicular Ad-hoc Networks (VANET'S) have become viable and valuable for their wide variety of novel applications to improve driver's experience. The topology of network is highly time varying due to high mobility of vehicular nodes. This makes challenging to detect and diagnose errors in software applications used in the vehicles. Software reliability in vehicles is critical factor and significant challenge to be met. Misbehaving and faulty software applications in vehicle have to be detected and diagnosed from disrupting operation as it is hard to address in life critical vehicular network environment. The work proposes an advanced diagnostics system to be loaded in Road Side Units (RSU's) so that operating software is periodically transmits the codes generated by the vehicle configured with OBD to the RSU for test. The software is diagnosed at the RSU accessing the data from cloud servers for reliability. Later, a fixed patch is transmitted back to the vehicle via RSU's. The result in this paper shows the analysis of different temperature variables used in vehicles and are efficiently measured.
Uploads
Papers by deepa saibannavar