Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
A Survey of Existing E-mail Spam Filtering Methods Considering Machine Learning Techniques
Get PDFE-mail is one of the most secure medium for online communication and transferring data or messages through the web. An overgrowing increase in popularity, the number of unsolicited data has also increased rapidly. To filtering data, different approaches exist which automatically detect and remove these untenable messages. There are several numbers of email spam filtering technique such as Knowledge-based technique, Clustering techniques, Learningbased technique, Heuristic processes and so on. This paper illustrates a survey of different existing email spam filtering system regarding Machine Learning Technique (MLT) such as Naive Bayes, SVM, K-Nearest Neighbor, Bayes Additive Regression, KNN Tree, and rules. However, here we present the classification, evaluation and comparison of different email spam filtering system and summarize the overall scenario regarding accuracy rate of different existing approache
A Model for Congestion Mitigation in Long-Term Evolution Networks Using Traffic Shaping
Get PDFLong-Term Evolution (LTE) has evolved the field of data transmission, bringing about the era of 4th Generation Networks capable of providing broadband speeds to mobile users based on the development experienced in the field of data transmission. There has been a sporadic increase in the utilization of Long-Term Evolution (LTE) networks, due to the ever-growing utilization of network links and network services, certain issues begin to rise, one of such issues is the problem of congestion. The more utilized a network becomes, the more vulnerable it is to congestion. Data networks become congested when network cannot keep up with the growing demand for the networks resources. The focus of this work is on proposing a model to mitigate the effects of congestion on Long-Term Evolution (LTE) networks. The model was evaluated using the NS-2 network simulator and Network Utilization, Network Delay, Throughput metrics would be used to evaluate the efficiency of the model. The enhanced model performed better and more efficiently than previous solutions, offering a better way to mitigate the effects of congestion in Long-Term Evolution networks. The results obtained from the simulations showed that the enhanced model if implemented in Long-Term Evolution network will reduce the effects of congestion, improving network throughput and overall performance
An E-Passport System with Multi-Stage Authentication : A Casestudy of the Security of Sri Lankaas E-Passport
Get PDFE-passport or Electronic passport is one of the newly established research areas, especially since in the last few years there have been numerous reported attempts of illegal immigration across a number of country borders. Therefore, many countries are choosing to introduce electronic passports for their citizens and to automate the verification process at their border control security. The current e-passport systems are based on two technologies: RFID and Biometrics. New applications of RFID technology have been introduced in various aspects of people2019;s lives. Even though this technology has existed for more than a decade, it still holds considerable security and privacy risks. But together with RFID and biometric technologies an e-passport verification system can reduce fraud, identity theft and will help governments worldwide to improve security at their country borders. In 2017 Sri Lankan government proposed to introduce a new epassport scheme which will contain embedded RFID tags for person identification purpose. Therefore, this paper proposes a novel multi-stage e-passport verification scheme based on watermarking, biometrics and RFID
Spark Big Data Analysis of World Development Indicators
Get PDFWe would like to analyze different development indicators such as life expectancy of a country, patent applications by residents, and trademark of applications which serves as great analyzation for the Business Analysts, Financial Analysts, and Data Scientists. Data set is collected from the World Bank websites, for this analysis, which has world development indicators with respect to the country. The data is analyzed based on the yearly timeline, geographical locations on the map and also top 10 countries for a particular world development indicator. Moreover, it has found that the countries where the life expectancy is high the people are more creative and the patent applications are created on a huge scale. Also, the trademark applications are more where the life expectancy is higher. This analysis provides insights on the world development indicators. In the paper, data analysis is done on a huge dataset by using Spark on Hadoop Big Data cluster and its visualization charts are presented
Application of Ethereum Smart Contracts in Purpose of Generating New Cryptocurrencies
Get PDFAs Bitcoin2019;s popularity increases so does the familiarity with cryptocurrencies in general. Ethereum is one of the most popular platforms in the cryptocurrency world. Development of a cryptocurrency using programming language Solidity and Ethereum platform is presented in this paper. Following the development, possible utilization of this cryptocurrency will be discussed
Using Neural Networks to Design Transistor Amplifier Circuits
Get PDFThis paper is an extension of previous work that addressed the application of bipolar transistor amplifier design using neural networks That work addressed the design of common emitter amplifiers by first mathematically determining specific output parameters from a large selection of biasing resistors Once the outputs had been determined a neural network was trained using the aforementioned results as inputs and the biasing resistors as outputs This was initially performed with ideal emitter bypass capacitors but was then followed-up by employing several non-ideal capacitors making it much more interesting and useful This paper focuses on the common collector and the common base configurations Bipolar junction transistor amplifier parameters often include voltage gain input impedance output impedance and the voltage difference between the collector and emitter These will be addressed in this paper as before There are several methods that can provide a suitable solution for each design however the objective of this work is to indicate which external resistors are necessary to yield useful results by employing neural network
New Algorithm For Detection of Spinal Cord Tumor using OpenCV
Get PDFThe spinal cord one of the most sensitive and significant parts of the human body lies protected inside the spine the backbone and contains bundles of nerves Any minor problem in the spinal cord can cause debilitation of internal and external functions of the human body One of the complications in the spinal cord is tumor - abnormal growth of tissue In this project we present a new algorithm based on OpenCV to detect spinal cord tumors from MRI sagittal image without human intervention The new algorithm can detect tumor-like substances adjacent to the spinal cord Tests carried out on spinal cord MRI images 33 cervical spinal images showed approximately 90 91 of accuracy rate in detecting tumor
Load Balancing in Cloud Computing: A Survey on Popular Techniques and Comparative Analysis
Get PDFCloud Computing is universally accepted as the most intensifying field in web technologies today. With the increasing popularity of the cloud, popular website2019;s servers are getting overloaded with high request load by users. One of the main challenges in cloud computing is Load Balancing on servers. Load balancing is the procedure of sharing the load between multiple processors in a distributed environment to minimize the turnaround time taken by the servers to cater service requests and make better utilization of the available resources. It greatly helps in scenarios where there is misbalance of workload on the servers as some machines may get heavily loaded while others remain under-loaded or idle. Load balancing methods make sure that every VM or server in the network holds workload equilibrium and load as per their capacity at any instance of time. Static and Dynamic load balancing are main techniques for balancing load on servers. This paper presents a brief discussion on different load balancing schemes and comparison between prime techniques
Monitoring Unscheduled Leaves using IVR
Get PDFLeaves are inherent part of a work and employees do take leaves at some point of this work life. Different types of leaves are provided by various employers in India. Some leaves are more informal in nature (also called as unscheduled leaves) compared to formal type of leaves (also called as scheduled leaves), one such unscheduled type of leave is Causal Leave (CL). These leaves are availed by employees in case some causality occurs with him/her or in his/her known ones. As the nature of CL is more of informal, it is believed that employee can take it as and when required and inform the authorities when he/she resumes his/her work. Currently most of the leave applications available are either in form of proforma (paper based) or web-based (online system). Many employees at the time of taking CL do not have both this options available, so even if they wish to inform about their leaves they have no mechanism to do so. Through this paper, we will to explore Interactive Voice Response (IVR) based Leave Management wherein we can provided a third option by high he/she can register his/her CL in his/her organization
Facial Age Estimation
Get PDFAge estimation based on the human face remains a significant problem in computer vision and pattern recognition. In order to estimate an accurate age or age group of a facial image, most of the existing algorithms require a huge face data set attached with age labels. This imposes a constraint on the utilization of the huge amount of human photos in the social networks. These images may provide no age label, but it is easily to derive the age difference for an image pair of the same person. To improve the age estimation accuracy, we propose a novel learning scheme to take advantage of these weakly labeled data via the deep Convolutional Neural Networks (CNNs). For each image pair, Kullback-Leibler divergence is employed to embed the age difference information(MS. SWATHI THILAKAN). The entropy loss and the cross entropy loss are adaptively applied on each image to make the distribution exhibit a single peak value. The combination of these losses is designed to drive the neural network to understand the age gradually from only the age difference information. Experimental results on two aging face databases show the advantages of the proposed age difference learning system and the state-of-the-art performance is gained