Browsing by Author "Shanmugapriya, D"

Now showing 1 - 20 of 20
  • No Thumbnail Available
    Item
    Acoustic Signal based Feature extraction for Vehicular Classiflcation
    (2010) Shanmugapriya, D
    Acoustic signal classification consists of extracting the features from a sound, and of using these features to identify classes the sound is liable to fit.. Different types of noise coming from different vehicles mix in the environment and identifying a particular vehicle is a challenging one. Feature Extraction is done to identify the characteristic of the vehicle. The characteristic of each vehicle will be used to detect its presence and classify its type. Six different features of the vehicle acoustic signals are calculated and then further utilized as input to the classification system. These features include Signal Energy, Energy Entropy, Zero-Crossing Rate, Spectral Roll-Off, Spectral Centroid and Spectral Flux. All these features are extracted from each and every acoustic signal of the vehicles.
  • No Thumbnail Available
    Item
    Applying Computational Intelligence Techniques for Personal Authentication using Keystroke Dynamics
    (2013) Shanmugapriya, D
    ABSTRACTUsername -with password is the commonly used authentication mechanism for securing huge data transactions being carried out everj' day via Internet. Most of the text based authentication methods arc vulnerable to manv attacks as thev depend on text and can be strengthened more by combining password with key typing manner of the user. Keystroke Dynamics is one of the inexpensive and strong beliavioral biometric technologies, which identifies the authenticity of a user when the u.ser is working via a keyboard. Tlic paper uses computational intelligence tcehnkiues such as Genetic algorithm. Ant Colony Optimization and Particle Swarm Optimization for feature sub.set selection and back propagation Neural Nebvork for classification. From the results, it is observed that ACO wrapped with BPN outperforms the other methods.
  • No Thumbnail Available
    Item
    Cloud Insider Threat Detection using Deep Learning Models
    (2023-05) Dhanya, C J; Shanmugapriya, D
  • No Thumbnail Available
    Item
    Digital Watermarking Technique in Vehicle Identification using Wireless Sensor Networks
    (2010) Shanmugapriya, D
    Wireless Sensor networks (WSN) is an emerging technology and have great potential to be employed in critical situations like battlefields and commercial applications such as building, traffic surveillance, habitat monitoring and smart homes and many more scenarios. This paper discusses about digital watermarking technique in vehicle acoustic signals for vehicle identification using Wireless Sensor Networks. Vehicle identification means, identifying the category of the vehicle. The assumed category here may be friend or foe. The Digital Watermarking technique has been introduced to make the vehicle acoustic signals authenticated. The vehicle acoustic signals belong to the friend category are authenticated using digital watermarking technique and the signals are embedded into digital watermarking technique to represent it uniquely. Here the step by step process of embedding the digital watermarking technique is discussed along with the results. Once the embedding of the digital watermarking technique is done, the resultant signals are further used for vehicle identification or classification.
  • No Thumbnail Available
    Item
    An Efficient Feature Selection Technique for User Authentication using Keystroke Dynamics
    (2011) Shanmugapriya, D
    Securing the sensitive data and computer systems by allowing ease access to authenticated users and withstanding the attacks of imposters is one of the major challenges in the field of computer security. ID and password are the most widely used method for authenticating the computer systems. But, this method has many loop holes such as password sharing, shoulder surfing, brute force attack, dictionary dttack, guessing, phishing and many more. Keystroke Dynamics is one of the famous and inexpensive behavioral biometric technologies, which identifies the aulhenticity of a user when the user is working via a keyboard. Keystroke features like dwell time, flight time, di-graph, trigraph and virtual key force of every user are used in this paper. For the purpose of preprocessing Z-Score method is used. Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA) algorithm is used with Extreme Learning Machine (ELM) for feature subset selection. In order to classify the obtained results ELM algorithm is used. Comparison of ACO, PSO and GA with ELM respectively is done to find the best method for feature subset selection. From the results, it is revealed that ACO with ELM is best for feature subset selection.
  • No Thumbnail Available
    Item
    Face Mask Detection Using Machine Learning and Deep Learning
    (2021-05) Preethi, M; Shanmugapriya, D
  • No Thumbnail Available
    Item
    Feature Subset Selection using PSO-ELM-ANP Wrapper Approach for Keystroke Dynamics
    (2012) Shanmugapriya, D
    The security of computer access is important today because of huge transactions being carried out every day via the Internet. Username with password is the commonly used authentication mechanism. Most of the text based authentication methods are vulnerable to many attacks as they depend on text and can be strengthened more by combining password with key typing manner of the user. Keystroke Dynamics is one of the famous and inexpensive behavioral biometric technologies, which identifies the authenticity of a user when the user is working via a keyboard. The paper uses a new feature Virtual Key Force along with the commonly extracted timing features. Features are normalized using Z-Score method. For feature subset selection, a wrapper based approach using Particle Swarm Optimization—Extreme Learning Machine combined with Analytic Network Process (PSO-ELM-ANP) is proposed. From the results, it is observed that PSO-ELM-ANP selects less number of features for further processing.
  • No Thumbnail Available
    Item
    Fractal Image Compression Techniques
    (2010) Shanmugapriya, D
  • No Thumbnail Available
    Item
    A Hybrid Approach for Acoustic Signal Segmentation by Computing Similarity Matrix, Novelty Score and Peak Detection for Vehicular Classification in Wireless Sensor Networks
    (2010) Shanmugapriya, D; Padmavathi, G
    Vehicle acoustic signals have long been considered as significant source in sensor networks for classification. In this research acoustic signals generated by each vehicle will be used to detect its presence and classify the type. Vehicle acoustic signal segmentation is important for continuous signal recognition because it reduces the search space effectively in vehicle’s signal recognition. However, for Vehicle classification, it is difficult to segment the signal input reliably into useful sub-units because i) vehicle sound units can often be located roughly via intensity changes ii) energy changes in signal spectrum or amplitude help to estimate unit boundaries, but these cues are often unreliable. In this paper the series of steps proposed are signal segmentation is presented, includes decomposition of signals into successive frames of 50 ms without overlap. The computations of the spectrum representation (FFT) of the frames are carried out. The similarity matrix that shows the similarity between the spectriims of different frames is computed. Estimation of the novelty score related to the similarity matrix is done. The detection of the peaks in the novelty score is made and finally segmenting the vehicle acoustic signals using the peaks as position is done. These segmented signals are further used for feature extraction and '■'assification.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Indian Traffic Sign Detection Using Machine Learning and Deep Learning
    (2021-05) Dharani, T; Shanmugapriya, D
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Keystroke Dynamics authentication using Data Fiitering Techniques and Neurai Network Approaches
    (2010) Shanmugapriya, D
    bcuring the secret data and computer systems by allowing ase access only to the authenticated users and enduring the ^ k s of imposters is one of the major challenges in the of computer security. Traditionally, user name and ■sssvord schemes are widely used for controlling the access B computer systems. But, this scheme has many flaws such B Password sharing. Shoulder surfing. Brute force attack, ISctionary attack, Guessing, Phishing and many more. Sametrics technologies provide more reliable and efficient »52ns of authentication and verification. Keystroke S^namics is one of the famous biometric technologies, i ^ h will try to identify the authentication of a user when be user is working with a keyboard. In this paper, neural Wnork approaches with keystrokes for three different jBss>N'ords namely weak, medium and strong passwords are Bten into consideration. Neural Network algorithms are azended by applying normalization techniques for data fflsring before performing the classification on the datasets. iSe performance of normalization based neural network ^ rithm s is compared against neural network algorithms all different category of passwords and the accuraey lijtained is compared.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    A Method for Preprocessing the Dwell Time and Flight Time of Biometric Keystroke Templates
    (2010) Shanmugapriya, D; Padmavathi, G
    ecuring the sensitive data and computer systems by allowing ease access to authenticated users and withstanding the attacks J o t imposters is one of the major challenges in the field of computer security. Traditionally, ID and password schemes are most widely used for controlling the access to computer systems. But, this scheme has many flaws such as Password Sharing, Shoulder Surfing, Brute Force Attack, Dictionary Attack, Guessing, Phishing and many more. The Uniqueness of Biometrics for any specific human being provides more reliable and efficient means of authentication and verification. Keystroke Dynamics is one of the famous and inexpensive behavioural biometric technologies, which will try to identify the authenticity of a user when the user is working via a keyboard. The objective of the paper is to preprocess the obtained dwell time and flight time using Z-score in order to obtain the tolerable False Acceptance Rate and False Rejection rate.
  • No Thumbnail Available
    Item
    A Study on Vehicle Detection and Tracking Using Wireless Sensor Networks
    (2010) Shanmugapriya, D; Padmavathi, G
    Wireless Sensor network (WSN) is an emerging technology and has great potential to be employed in critical situations. The development of wireless sensor networks was originally motivated by military applications like battlefield surveillance. However, Wireless Sensor Networks are also used in many areas such as Industrial, Civilian, Health, Habitat Monitoring, Environmental, Military, Home and Office application areas. Detection and tracking of targets (eg. animal, vehicle) as it moves through a sensor network has become an increasingly important application for sensor networks. The key advantage of WSN is that the network can be deployed on the fiy and can operate unattended, without the need for any pre-existing infrastructure and with little maintenance. The system will estimate and track the target based on the spatial differences of the target signal strength detected by the sensors at different locations. Magnetic and acoustic sensors and the signals captured by these sensors are of present interest in the study. The system is made up of three components for detecting and tracking the moving objects. The first component consists of inexpensive off-the shelf wireless sensor devices, such as MicaZ motes, capable of measuring acoustic and magnetic signals generated by vehicles. The second component is responsible for the data aggregation. The third component of the system is responsible for data fusion algorithms. This paper inspects the sensors available in the market and its strengths and weakness and also some of the vehicle detection and tracking algorithms and their classification. This work focuses the overview of each algorithm for detection and tracking and compares them based on evaluation parameters.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Video Pre-Processing of Image Information for Vehicle Identification
    (2011) Padmavathi, G; Shanmugapriya, D
    This paper presents a video-based vehicle identification system which consists of preprocessing, segmentation, object extraction, object tracking and vehicle classification. The linear and non-linear filtering teehniques are adopted here to filtering the video sequences for noise removal. Image filtering algorithms are applied on videos to remove the different types of noise that are either present in the video during capturing or injected in to the video during transmission. In this work the different filtering algorithms are adopted and the performances of the filters are eompared using Peak Signal to Noise Ratio (PSNR) and Mean Square Error (MSE).
  • No Thumbnail Available
    Item
    Vulnerability Analysis Using Unsupervised Machine Learning Methods
    (2022-05) Megha sree Kannaiah, K; Shanmugapriya, D