Volume 10, Issue 2, February 2018

 

 

Efficiency of LSB and PVD Algorithms Used in Steganography Applications
 

Efficiency of LSB and PVD Algorithms Used in Steganography Applications

Pages: 20-29 (10) | [Full Text] PDF (2.67 MB)
B Rexha, P Rama, B Krasniqi, G Seferi
Faculty of Electrical and Computer Engineering, University of Prishtina, Kodra e Diellit p.n.10000 - Prishtina, Kosovo

Abstract -
Steganography is the science of hiding secret information in other non-suspicious information allowing secret communication between parties. The steganographic process consists of secret information, the carrier file and steganographic algorithm. Each carrier has its own characteristics which affects the steganographic algorithm. However, what differentiates a steganographic algorithm from another is the efficiency for data hiding in the carrier. An algorithm is more efficient if it hides more secret information while maintaining the quality of the carrier. This paper compares different parameters that affect efficiency of LSB and PVD algorithms, impact of carrier type, format, and size. All these analyzes were done using SteganoFIEK application, developed in the framework of this paper, for experimental purposes. Furthermore, SteganoFIEK implementation of LSB is compared against other open-source applications.
 
Index Terms - Steganography, Steganalysis, LSB, PVD, Efficiency, Security

Citation - B Rexha, P Rama, B Krasniqi, G Seferi. "Efficiency of LSB and PVD Algorithms Used in Steganography Applications ." International Journal of Computer Engineering and Information Technology 10, no. 2 (2018): 20-29.

A Novel Real-time Human Activity Based Anomaly Detection Model Using Graph Based Clustering and Classification Model
 

A Novel Real-time Human Activity Based Anomaly Detection Model Using Graph Based Clustering and Classification Model

Pages: 30-36 (7) | [Full Text] PDF (469 KB)
D Kishore, MC Mohan, AA Rao
Asst.Prof, Department of Computer Science & Engineering, Andhrapradesh, India

Abstract -
Detecting online abnormality in the video surveillance is a challenging issue due to streaming, video noise, outliers and resolution. Traditional trajectory based anomaly detection model which analyzes the video training patterns for anomaly detection. This paper aims to solve the problem of video noise and anomaly detection .In this paper, a novel filtered based ensemble clustering and classification model was implemented using the threshold based method, graph based clustering algorithm and classification model. Experimental results proved that the proposed model has high computation detection rate compared to traditional real-time anomaly detection models.
 
Index Terms - Anomaly Detection, Video Anomaly, Graph Based Clustering Model

Citation - D Kishore, MC Mohan, AA Rao. "A Novel Real-time Human Activity Based Anomaly Detection Model Using Graph Based Clustering and Classification Model." International Journal of Computer Engineering and Information Technology 10, no. 2 (2018): 30-36.

Text Parsing with Markov Logic Network
 

Text Parsing with Markov Logic Network

Pages: 37-40 (4) | [Full Text] PDF (554 KB)
N Wang
University of Michigan, 599 N Mathilda Ave, Sunnyvale, CA 94085, USA

Abstract -
This document describes a novel way to extract structure information from plain text using Markov Decision Process. In the age of big data, unstructured information such as text, photos and videos becomes abundant. However, data warehouse requires structured data with well-defined schema. It has been a challenge for the computer science community to extract useful data under strict schema from unstructured data schema. Here we proposed an automated system that is able to understand and infer the most likely counterpart in text stream that corresponds to a filed under the requested schema. The designed algorithm formulated the plain text using context dependent grammar with various weights, which would be sued to decide which field of the structured schema a particular piece of unstructured data belongs to. A machine-learning algorithm is used to learn the weights from training data. We implemented this automated system and applied it to extract schema data from plain US bankruptcy petition forms.
 
Index Terms -

Citation - N Wang. "Text Parsing with Markov Logic Network." International Journal of Computer Engineering and Information Technology 10, no. 2 (2018): 37-40.