Browsing by Author "Radha, V"

Now showing 1 - 20 of 79
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    ADAPTING RUNGE - KUTTA LEARNING ALGORITHM IN ANFIS FOR THE PREDICTION OF COD FROM AN UP-FLOW ANAEROBIC FILTER
    (2013) Radha, V
    Water consumes vast area in the earth’s surface and safe drinking water is essential for humans and other organisms to survive in the world. Eliminating waste matters from water is the necessary requirement nowadays. The ultimate purpose of wastewater treatment is the protection of good quality water which is the most priceless resource. Use of Artificial Neural Network (ANN) models is gradually increasing to predict wastewater treatment plant variables. This detection helps the operators to take proper action and manage the process accordingly as per the norms. Anaerobic processes are often preferred to aerobic processes for treating waste streams that contain high Chemical Oxygen Demand (COD) concentrations. Up-flow Anaerobic Filter (UAF) is a common process used for various anaerobic wastewater treatments. COD is used to measure the strength (in terms of pollution) of waste water. COD level in the effluents of the UAF determines the pollutants in the wastewater. The proposed method uses cheese whey as an influent. It is tested in the anaerobic reactor using COD test to predict the level of oxygen requirement of the effluent. Predicting the effluent parameters is a time consuming process when using Classical Models as it involves complexity and high non-linearity. Hence the proposed method uses an efficient technique namely Z-Score Normalization technique as a preprocessing step. Particle Swarm Optimization (PSO) for feature selection process and Adaptive Neuro-Fuzzy Inference System (ANFIS) with RungeKutta Teaming Method (RKFM) as a learning algorithm is used for prediction of COD. Experiments conducted on a real data indicates that tlie application of Z-Score normalization schemes followed by a PSO feature selection and ANFIS with RKLM prediction results in better performance compared to other methods.
  • No Thumbnail Available
    Item
    ANOMALY DETECTION AND APPLICATIONS - A STUDY
    (2013) Radha, V
    Anomaly detection is a major area in different ground of Research and Applications. Anomaly Detection (AD) is to find entire objects which are different from other objects. Various techniques of anomaly deteetion are developed for individual domain This paper describes the concept of anomaly, causes of anomalies, classification of Anomaly Detection, various domains with techniques of anomaly deteetion.
  • No Thumbnail Available
    Item
    Anti-Theft Application For Android Based Device
    (2016-04) Bhavani Shobana, B; Radha, V
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Automated Network Backup System
    (2004-04) Bindy Jose; Radha, V
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Backend Automation Tool
    (2014-03) Shalini, K; Radha, V
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    A Brief Study in Noise and Filtering for Dermoscopic Images
    (2016) Radha, V
    Noise is one of the main problems of digital image processing. The noise in an image is a disturbance while performing operations in the image processing. Medical images plays vital role in digital image processing. In dermoscopic images, the unwanted hairs on skin lesion, air bublles etc., are considered as noise. Noise can be removed in the preprocessing stage through filtering. Filtering is the technique used in preprocessing to make the image a clear and eligible manner so that other process can be further continued without any disturbances. This paper mainly focuses on the noise in an image and filtering used to remove the noise.
  • No Thumbnail Available
    Item
    Combined Speaker Recognition and Compression for Secured Speech Transmission
    (2014) Radha, V
    The continued advancement and growth in the network processing ability have improved the competence and scope of speech communication in the network. Therefore the secure speech communication and security of communication information are required now a days. To provide more security for the speech signal, the Multiple Huffman Table (MHT) is enhanced in this paper, by incorporating an optimization procedure as a preprocessing step before compression. So before performing compression the MHT splits the speech signal into Most Significant Signal (MSS) and Least Significant Signal (LSS). MSS is considered to be the significant signal, so the MHT considers only the MSS for compression. From the compressed output, the coefficients are selected and protected using cryptographic cipher Advanced Encryption Standard (AES), because it will be difficult for attackers to recover any information from these coefficients. Finally the results were evaluated using Compression ratio (CR), Peak Signal-to-Noise Ratio (PSNR) and Normalized Root-Mean Square Error (NRMSE). From the results it can be seen that the Enhanced MHT with Encryption method provides better result.
  • No Thumbnail Available
    Item
    Comparative Analysis of Partial Occlusion Using Face Reco g nitio n Tech n iq u es
    (2013) Radha, V
    This paper presents a comparison of partial occlusion using face recognition techniques that gives In which technique produce better result (or total success rata. The partial occlusion of (ace recognition is especiaily useful (or people where part of their face Is scarred and defect thus.need to be covered. Hence, either top part/eye region or bottom part of face will be recognized respectively. The partial face Information are tested with Principle Component Analysis (PCA), Non-negative matrix factorization (NfvlF), Local NMF (LNMF) and Spatially Confined NMF (SFNMF). The comparative results show that the recognition rate of 95.17% with r = 80 by using SFNMF (or bottom face region. On the other hand, eye region achieves 95.12% with r = 10 by using LNMF.
  • No Thumbnail Available
    Item
    COMPARISON OF ENHANCED SCHEMES FOR AUDIO CLASSIFICATION
    (2013) Radha, V
    In the modem era of communication, audio plays an important role in understanding a digital media. Due to the rise of economical audio capturing devices, the amount of audio data available both online and offline is enormous and techniques that can automatically classify and retrieve these audio data is an immediate need. An automatic content based audio classification and retrieval system consists of three modules namely, feature extraction, classification and retrieval. This paper presents a comparative smdy of two algorithms that performs these three steps in different manners. The performance of the selected systems are analyzed while using four different features (acoustic, percepmal, mel-frequency cepstral coefficients (MFCC) and a ''"mbination of percepmal and MFCC) and four classifiers that enlianced Support Vector Machine (SVM) and Centroid Neural itwork (CNN) along with its base versions, SVM and CNN. Experimental results showed that the enhanced SVM algorithm when using the combined feature vector produced improved accinacy and reduced error rate.
  • No Thumbnail Available
    Item
    Comparison of Image Preprocessing Techniques for Textile Texture Images
    (2010) Radha, V
    Texture analysis is an important approach in textile quality control. The investment in automated unit is more economical when reduction in labor cost and associated benefits are considered. Preprocessing in textile image is a crucial initial step before texture analysis is performed. Many preprocessing methods are available in the literature. Datasets are limited by laboratory constraints so that the need is for guidelines on quality and robustness, to proceed experimentation while image are yet restricted. In this paper, the performance of four preprocessing methods are compared namely Contrast adjustment. Intensity adjustment. Histogram equalization, Binarization and Morphological operation. The performances of these methods are evaluated using Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE).
  • No Thumbnail Available
    Item
    Comparison of Layer and Block Based Classification in Compound Image Compression
    (2011) Radha, V
    The compound image compression normally based on three classification methods th at is object based, layer based and block based. This paper presents a comparison of layer and block based classification methods. For secure transmission, an encryption algorithm was used to encrypt the compressed image .Experimental results were conducted to analyze the performance of the two compressors.
  • No Thumbnail Available
    Item
    Contrast Stretching and Non Linear Median Filters for Fabric Inspection
    (2011) Radha, V
    In automatic fabric inspection, fabric image acquires impulse noise due to malfunctioning in camera sensors, faulty memory locations in hardware, or transmission via a noisy channel. Eliminating such noise is an important preprocessing task. The fabric image should be enhanced to achieve a high interpretability of perception to detect defects. In this paper contrast stretching, grey level thresholding and median fdters are used to enhance the fabric image. The performances of these methods are evaluated using Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE). The contrast stretching with spatial median filter gives suitable results to enhance the perception of defects.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Cross Language Text Retrieval: A Review
    (2012) Radha, V
    The World Wide Web has evolved into tremendous source of information and , it continues to grow at exponent rate. Now a daj’s web servers are storing different types of contents in different languages and their usage ' is increasing rapidly. According to Online Computer Library Center, English is still a dominant language in the Web. Only small percentage of population is familiar with English language and they can express their queries in English to access the coifient in a right way. Due to globalization, content storage and retrieval must be possible in Si languages, which is essential for developing nations like India. Diversity of langu%es is becoming great barrier to understand and enjoy the benefits in digital world. Cross Language Information Retrieval (CLER) is a subfield of Information retrieval; user can retrieve the objects'in a^ language different from the language of query expressed. These objects may be text documents, passages, audio or video and images. Cross Language Text Retrieval (CLTR) is used to’" return text documents in a ' language * other than query language. CLTR technique allows crossing the language barrier and accessing the web content in an efficient way. This paper reviews some types of translations carried out in CLTR, ranking methods used in retrieval of documents and some of their related works. It alsor'discusses about various approaches and their evaluation measures used in various applications.
  • No Thumbnail Available
    Item
    Developing Mobile Agents for Remote Monitoring
    (2007-04) Radhika, G; Radha, V