Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Mathematical and Computer Modeling of the State of Complex Systems under the Influence of Potential Forces
Full text linkThis article considers the problem of determining critical points and areas in a system that is exposed to external forces As a result the system can lose its stability and go into a non-equilibrium state and then collapse and cause various kinds of catastrophes The study of the problem of identification and prediction of disasters is relevant because allows you to take preventive measures to prevent them and reduce the risks of various negative scenario
Fabric Defect Detection using Image Processing
Full text linkFabric defect is one of the most important and serious matters of quality control in textile industry in Bangladesh. This task takes a lot of time and money. For this reason we have introduced a simple process to find defects on fabric based on edge detection. This process is mainly focused on image processing which can be integrated with fabric defect detection automation system. In this paper we have tried a new approach using the filter method with edge detection and found good results. Our algorithm can detect defected fabric area successfully. It can be also used in real-time defect detection considering light intensity, zoom, fabric width, camera resolution etc. As our algorithm mainly works on the principle of edge detection, it cannot detect defect on multicoloured or patterned fabric. It works well on single coloured fabric without any fold or edg
Biological Analysis and Linear Block Hidden Markov Model for Gene and Labelled
Full text linkHidden Markov models (HMMs) have been extensively used in biological sequence analysis . HMMs and their applications in a variety of problems in molecular biology .The difficulty of using computational approaches to discover genes in DNA sequences is yet unsolved. gene prediction from within genomic DNA are far from being powerful enough to elucidate the gene structure completely. We develop a hidden Markov model (HMM) to represent the degeneracy features of splicing junction donor sites in eucaryotic genes. he HMM system is fully rained using an expectation maximization algorithm and the system performance is evaluated using the 10-way cross-validation method. he HMM system is fully trained using an expectation maximization algorithm and the system performance is evaluated using the 10-way cross-validation method
Comparison of Effective Bandwidth Estimation Methods for Data Networks
Full text linkAbstract-The purpose of this work is to apply techniques to estimate the Effective Bandwidth, from traffic traces, for the Generalized Markov Fluid Model in data networks. This model is assumed because it is versatile in describing traffic fluctuations. The concept of Effective Bandwidth proposed by Kelly is used to measure the channel occupancy of each source. Since the estimation techniques we will use require prior knowledge of the number of clustering clusters, the Silhouette algorithm is used as a first step to determine the number of classes of the modulating chain involved in the model. Using that optimal number of clusters, the Kernel Estimation and Gaussian Mixture Models techniques are used to estimate the model parameters. After that, the performance of the proposed methods is analyzed using simulated traffic traces generated by Markov Chain Monte Carlo algorithms
Use of Techniques and Tools for Investigative Process in Computational Forensic Expertise
Full text linkComputer forensics investigates and retrieves information about a fact, as well as examining digital evidence that can be decisive in any technological situation. The research will explain techniques that are used during the expertise, ensuring the integrity of the data so that the analysis is not impaired. First, a bibliographic survey will be carried out in search of concepts about data collection and analysis techniques in the forensic area. The method includes performing procedures such as equipment identification and chain of custody in a simulated environment, in order to determine the best mechanism for the presented scenario. Finally, the main steps and forensic tools were presented for a better way in which the expert can use to perform the exact analysis of the crime
Design of Automated Database System for Storage and Management of Reports on Mycotoxins Contaminated Agricultural Products in Sub-Saharan Africa
Full text linkThis paper discusses the idea and the design of an automated system for storage and management of mycotoxins reports for decision making Mycotoxins are poisonous chemical compounds produced by certain fungi Mycotoxins are fungal secondary metabolites that contaminate various feedstuffs and agricultural crops The contamination of food by mycotoxins can occur before production during storage processing transportation or marketing of the food products High temperature moisture content and water activity are among the factors that facilitate the production of mycotoxins in food The five major mycotoxins produced in food and feedstuffs are Aflatoxins ochratoxins fumonisins deoxynivalenol and zearalenon
An Improved Energy-Aware Distributed Unequal Clustering Protocol using BBO Algorithm for Heterogeneous Load Balancing
Full text linkWith the rapid extension of IoT-based applications various distinct challenges are emerging in this area Among these concerns the node s energy efficiency has a special importance since it can directly affect the functionality of IoT-Based applications By considering data transmission as the most energy-consuming task in IoT networks clustering has been proposed to reduce the communication distance and ultimately overcome node energy wastage However cluster head selection as a non-deterministic polynomial-time hard problem will be challenging notably by considering node s heterogeneity and real-world IoT network constraints which usually have conflicts with each other Due to the existence of conflict among the main system parameters various solutions have been proposed in recent years that each of which only considered a few real-world limitations and parameter
Accomplishment of Waterfall Model Exhausting Agile Data Science
Full text linkAgile information science is an technique to information technology targeted around net utility improvement It asserts that the handiest output of the information technological know-how procedure appropriate for effecting alternate in an organization is the net application It asserts that application development is a essential talent of a facts scientist consequently doing data science will become approximately constructing applications that describe the applied research procedure speedy prototyping exploratory data analysis interactive visualization and applied system gaining knowledge o
Neural Network Design using a Virtual Reality Platform
Full text linkThe evolution of Deep Learning (DL), a subset of machine learning, has made their use very effective in many artificial intelligence (AI) fields. In parallel Virtual Reality is going wide in many applications thanks to the proliferation of cameras in mobile devices and improved processing efficiency. Data visualization in deep learning is a fundamental element for which it can benefit from the advantages offered by the visualization of the VR for the development of the models. In addition, the researchers can widely use the editing of images and videos in the machine learning process to design a convolutional network suitable for image recognition. In this study, we want to demonstrate the usefulness of this approach in collecting data within virtual reality to train and optimize a convolutional neural network used to recognize human activities (HAR)
TrustPass Blockchain based Trusted Digital Identity Platform towards Digital Transformation
Full text linkAccording to the United States Census Bureau, by June 2019 world population on earth was 7.5 billion, which exceeds the world population of 7.2 billion as of 2015. Each of these citizens needs to prove their identity in order to fulfill their day-to-day routine. In this current digital revolution whole world is transforming to digitalization. Therefore, proving someones identity in the digital space is a must, because being able to track a person digitally can result in elimination of the identity theft and most incidents related to online harassments, while focusing on data privacy and security of citizens, we have proposed Trust Pass: Cyber Security Intelligence based trusted digital identity platform capable of registering and verifying service providers based on document validation neural network model (95.4% accuracy) and allowing citizens to authenticate themselves to service providers with three factor biometrics authentication with liveness detection neural network model (99.8% accuracy)