Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Past Before Future: A Comprehensive Review on Software Defined Networks Road Map
Get PDFSoftware Defined Networking (SDN) is a paradigm that moves out the network switch2019;s control plane (routing protocols) from the switch and leaves only the data plane (user traffic) inside the switch. Since the control plane has been decoupled from hardware and given to a logically centralized software application called a controller; network devices become simple packet forwarding devices that can be programmed via open interfaces. The SDN2019;s concepts: decoupled control logic and programmable networks provide a range of benefits for management process and has gained significant attention from both academia and industry. Since the SDN field is growing very fast, it is an active research area. This review paper discusses the state of art in SDN, with a historic perspective of the field by describing the SDN paradigm, architecture and deployments in detail
Optical Character Recognition based on Template Matching
Get PDFThis paper presents an innovative design for Optical Character Recognition (OCR) from text images by using the Template Matching method.OCR is an important research area and one of the most successful applications of technology in the field of pattern recognition and artificial intelligence.OCR provides full alphanumeric visualization of printed and handwritten characters by scanning text images and converts it into a corresponding editable text document. The main objective of this system prototype is to develop a prototype for the OCR system and to implement The Template Matching algorithm for provoking the system prototype. In this paper, we took alphabet (A-Z and a-z), and numbers (0-1), grayscale images, bitmap image format were used and recognized the alphabet and numbers by comparing between two images. Besides, we checked accuracy for different fonts of alphabet and numbers. Here we used Matlab R2018a software for the proper implementation of the system
Computer Vision Based Traffic Monitoring and Analyzing From On-Road Videos
Get PDFTraffic monitoring and traffic analysis is much needed to ensure a modern and convenient traffic system. However, it is a very challenging task as the traffic condition is dynamic which makes it quite impossible to maintain the traffic through traditional way. Designing a smart traffic system is also inevitable for the big and busy cities. In this paper, we propose a vision based traffic monitoring system that will help to maintain the traffic system smartly. We also generate an analysis of the traffic for a certain period, which will be helpful to design a smart and feasible traffic system for a busy city. In the proposed method, we use Haar feature based Adaboost classifier to detect vehicles from a video. We also count the number of vehicles appeared in the video utilizing two virtual detection lines (VDL). Detecting and counting vehicles by proposed method will provide an easy and cost effective solution for fruitful and operative traffic monitoring system along with information to design an efficient traffic model
Auditory Source Localization by Time Frequency Analysis and Classification of Electroencephalogram Signals
Get PDFThe temporal lobe or auditory cortex in the brain is involved in processing auditory stimuli. The auditory data processing capability in the brain changes as a person ages. In this paper, we use the hrtf method to produce sound in different directions as auditory stimulus. Experiments are conducted with auditory stimulation of human subjects. Electroencephalogram (EEG) recording from the subjects are made during the exposure to the sound. A set of time frequency analysis operators consisting of the cyclic short time Fourier transform and the continuous wavelet transform is applied to the pre-processed EEG signal and a classifier is trained with time-frequency power from training data. The support vector machine classifier is then used for source localization of the sound. The paper also presents results with respect to neuronal regions involved in processing multi source sound information
Cloud-based Architecture of Raspberry Pi: Personal Cloud Storage
Get PDFThe research explained the reason why we need personal cloud storage. This research will show steps on how to build a personal cloud storage by using credit card size Raspberry Pi (minicomputer), which will help the user to enable cloud storage mode to their external hard drive. However, other cloud storage services like Dropbox, Google Drive, and iCloud gives limited amount of storage. This research will help the users to use (1TB) or above size external hard drive to be use and have access anywhere from any device over internet. Also the second part of this research focus on replace the laptops to raspberry pi that lecturers use in the classroom to play PowerPoint slides, and videos at university. Universities use laptops to plug and play their educational slides and videos. All these laptops price and maintenance cost lot to the university, if we look deeply just for play slides we do not have to buy a laptop which cost 35 and it does not need any maintenance
Identification of Anesthesia Stages from EEG Signals using Wavelet Entropy and Backpropagation Neural Network
Get PDFThis study focuses on entropy based analysis of EEG signals for extracting features for a neural network based solution for identifying anesthetic levels. The process involves an optimized back propagation neural network with a supervised learning method. We provided the extracted features from EEG signals as training data for the neural network. The target outputs provided are levels of anesthesia stages. Wavelet analysis provides more effective extraction of key features from EEG data than power spectral density analysis using Fourier transform. The key features are used to train the Back Propagation Neural Network (BPNN) for pattern classification network. The final result shows that entropybased feature extraction is an effective procedure for classifying EEG data
Industry 4.0 2013; Robots with Distributed Mobility and Elements of Artifical Intelligence
No full textRobots artificial intelligence elements, which are a product and means of the Fourth Industrial Revolution, are a factor in the future development of the world's society. The present article proposes building a strategy for the future development of robotics by laying the principle of appropriately distributed mobility and functionality based and corresponding artificial intelligence. This principle corresponds to the millennial history of the Earth living beings evolution. The autors introduce new concepts such as kinematic, technological (professional) and structural-functional intelligence. It analyzes the connectivity of the internet, cyber-physical systems. There are three approaches proposed for design development: biological, engineering (industrial) and hybrid
A Cloud Mobile-Based Information Retrieval and Optimal Route Service Delivery System for Aiding the Treatment of Diabetic Patients in Nigeria
Get PDFDiabetes is considered as one of the most incurable diseases in the world. Studies have shown that at least fourteen million, four hundred and six thousand Nigerians are currently living with the incurable disease. Several researchers have proposed the use of mobile technology to aid diabetes treatment, but challenges such as time taken for physicians to attend to patients due to unavailable Information and problems associated with location of hospitals are recurrent. This research approached these challenges by developing a cloud mobile-based Information retrieval and optimal route service delivery system for aiding the treatment of diabetic patients in Nigeria
The Electric Field Driven Generator
Get PDFDr. Feynman predicted it to be theoretically possible to generate electric energy from an electric field. For realizing his predict, a new electrostatic generating method was proposed by the author that uses Asymmetric electrostatic force as the driving force of a charge carrier for the generator. Therefore this generator was named the electric field driven generator. After experimenting with many models using pendulum-type equipment, rotation-type equipment was tried. This experimental equipment produced electricity continuously when the applied voltage to the high voltage electrode was higher than 5.8 kV. This result was estimated by a simulation, and the measured collection currents for different high voltages almost agreed with the simulated collection current. Therefore the theory of the electric field driven generator was confirmed, and Feynman's dream has become reality
A Comparative Analysis of Air Pollution Detection Technique using Image Processing, Machine Learning and Deep Learning Approach
No full textAir pollution is one of the principal environmental issues for the industrial emission and infection of the atmosphere which is caused by the climatic and traffic elements burning of fossil fuels etc For the past several years various methods and models have been discovered to detect the pollution of the air In this paper among all of those three mechanisms have been focused which are image processing approach machine learning and deep learning technique A comparative study has developed among these three methods to detect the pollutant of the air in the account of time cost and efficiency so that different scenario and system can choose the best method according to their need The objective of this paper is to assimilate the procedure of these methods in brief and utilize this study to estimate the best solution for the corresponding requirement of any particular circumstance