Electrical distribution system suffers from various problems, such as reactive power burden, unbalanced loading, voltage regulation, and harmonic distortion. Though DSTAT-COMS are ideal solutions for these systems, they can be costly and have complexity compared to other reactive power compensation solutions. Phasewise-balanced reactive power compensations are required for fast-changing loads needing dynamic power factor correcting devices leading to terminal voltage stabilization. Static var compensators (SVCs) are preferred for these loads due to low cost and simple control strategy. These SVCs, while correcting power factor, inherently create harmonics due to the nonsinusoidal currents caused by the operation of thyristor-controlled reactors. This paper proposes minimizing the harmonics injected into the distribution systems with the operation of TSC-TCR-type SVC used in conjunction with fast-changing loads at the LV distribution level. The fuzzy logic system and ANNare used to solve this nonlinear problem, giving optimum triggering delay angles used to trigger thyristors in TCR. The scheme is attractive and can be used at SVC installations in distribution systems for steady-state reactive power compensation.Index Terms-Artificial neural network (ANN), fuzzy logic control, harmonic distortion, reactive power, static var compensators.

Breast cancer is the most common type of cancer among women in the world. Mammography is regarded as an effective tool for early detection and diagnosis of breast cancer. Microcalcification is one of the primary signs of breast cancer. There are various image texture analysis techniques for the detection of the microcalcifications. Screenfilm mammography is still the standard method used to detect early breast cancer, thus leading to early treatment. Digital mammography has recently been designated as the imaging technology with the greatest potential for improving the diagnosis of breast cancer. In this work a feature-based approach is used for analysis and classification of malignancy. Gray-level texture and Wavelet coefficient texture methods are used for feature extraction. Probabilistic Neural Network (PNN) is used for classification of images based on extracted features. The performance of classification by PNN based on features by texture method, wavelet method and combined methods are compared. The Receiver Operating Characteristics (ROC) Analysis is used for performance evaluation.

No abstract

Indian distribution systems are facing various power quality problems such as low power factor, harmonic distortion and reliability. SVC such as TSC-TCR is commonly used for balancing reactive power and correcting power factor. TSC-TCR type of compensators can compensate reactive powers of all the three phases independently by controlling the thyristors used in conjunction with TSC and delta connected Thyristor controlled reactors. TSC-TCR which are installed in distribution lines compensate unbalanced reactive power but while doing so the TCR injects harmonic currents of odd order into the point of common coupling. TSC-TCR types of SVCs have lower cost and moderately complex control strategy as compared to STATCOMs. This paper proposes a new method of controlling the injected harmonics of TSC-TCR system by using genetic algorithm based ANN training. The scheme can be effectively used at the existing TSC-TCR installations to reduce harmonic injections while catering to fluctuating loads.

Esophagitis is a condition of inflammation of the esophageal mucosa, which is also called as acid reflux disease. The cause maybe be due to slackness of the lower esophageal sphintcer which allows acidic contents of the food from stomach to esophagus. Esophagitis is detected by observing the esophagus by video endoscopy of the Upper Gastro-Intestinal tract. The classification of esophagitis is done by analyzing the images captured during the process of endoscopy. Classification of Esophagitis has many standards , with each standard having its plus and minus. The Los Angeles(LA) Classification deals with precise measurement of the mucosal breaks, for an image processing system to measure the mucosal breaks the position of the camera is to be known. We attempt to classify the Esophagitis using LA Classification without the camera position information using low level image features and classification is performed using a neural network classifier. The results of the classifier are compared with inter and intra observer variability studies. General Terms :Medical Diagnosis, Decision Support System