MAT Journals
Not a member yet
2487 research outputs found
Sort by
Performance Analysis of Machine Learning Algorithms in SMP: A Case Study of Twitter
Full text linkThe number of people using Social Media Platform (SMP) is increasing day by day. A few users may hide their identity with malicious intentions. Previous research has detected fake accounts created by bots using machine learning concepts. These ML concepts used engineered features such as the ‘following-to-followers ratio’ which is generally available in their accounts. In previous studies these similarly clustered features were applied to the machine learning models for detection of fake and real accounts. In the recent research the behavioural features like the sentient of the tweet posted on twitter is considered along with the parameters. Here, the ML models are also trained to use engineered features depending on behavioural data
An Improved Fault Tolerant Technique of Median Filter
Full text linkAcquisition noises in the digital image processing system basically made out of imprudent clamors, for example, hot and dead pixels, and for the most part expelled utilizing middle channels. The median filtering algorithm can be speedup by FPGA implementation. Configuration memory cells in SRAM based FPGAs are susceptible to radiation effects such as SEUs which leads to configuration memory bit flips and hence a protective measure is required for the proper operation of median filtering algorithm.The fault tolerant implementations of median filter provides a range for median value with which the calculated median value is checked and find out error if the median is out of the provided range. The main aim of the project is to fasten up the fault tolerant implementation of median filter in FPGAs by adding a few resources. Experimental results show that the proposed technique significantly reduces the latency of the fault tolerant median filtering process
Maximizing Resource Efficiency using Task Scheduling in Cloud
Full text linkConsidering the growing use of cloud computing and the want for best use of resources within the cloud, and attention to users that get services they use supported their pay-as-you-go basis, there ought to be a faster approach for users to decrease the user's waiting time and task's waiting time. The main purpose of this paper is to provide comparison between various task scheduling algorithms hence gives better understanding as to which algorithms aids better in maximizing resource efficiency and also enhance security by giving various layers of security. There are many scheduling algorithms within the world. In this paper, we have selected a few better working algorithms along the traditional max-min and min-min algorithms and also the security is enhanced using ECC encryption.
Use of Machine Learning in Detection of Phishing Websites
Full text linkMachine learning (ML) provides popular tools for data analysis. It has as of late indicated promising outcomes in battling phishing. ML techniques are appreciated to detect phishing attacks. Distinctive sorts of ML procedures have been utilized to serve the clients as an enemy of phishing device. The phishing site can be recognized dependent on some essential attributes like URL and Domain Identity, and security. Once a user makes a transaction online, during payment through the website our system will be useful. This application can be used by many E-commerce enterprises in order to make the whole transaction process secure. User can add extension file in the chrome. By using this extension file user can purchase the products from the online market without any hesitation. In this paper a blend of Decision Tree Algorithm alongside Apriori calculation of affiliation rule mining is utilized. Detecting Phishing Domains is a classification problem, so labeled data which has samples as phish domains are taken into account and legitimate domains are considered in the training phase. The dataset which is used in the training phase is a very important. This plays an important role in the building of a successful detection mechanism to be used for phishing. The uses of samples whose classes are precisely known are taken into consideration. The websites which are trusted will be declared as legitimate websites, similarly the websites which are not trusted will be declared as Phishing websites.The results generated are comparable to existing experiments published in literature. The system outputs indicate whether the website can be labeled as a phishing website.
Devising Methods to Avoid Formation of Defects in a Ball Bearing through FFT Analyzer
Full text linkMost of the essentials part is rolling element bearings in rotating machinery. Between the two parts of linear and relative motion are permitted for the function of bearings. During the operation, the bearings are often subjected to high speed and severe conditions. Under these severe operating conditions, defects are often developed in the bearing components. If no corrective measures are taken, the machine could halt or be seriously damaged. A different effect of bearing failure yields its own distinctive damage like primary damage and secondary damage are peeling and flaws. Excessive internal clearance, vibration, noise, are primary damage has been considered for the necessities. An unsuccessful bearing of times displays a mix of primary and secondary harm
Analysis of PZT/PVDF Actuated Cantilever Beams
Full text linkRecent advancement in the field of distributed sensor/actuators has led to the development of new structures called “smart structure”. A smart/intelligent structure is able to sense, respond and control its own characteristics and states, so as to significantly improve its operational performance. A structure becomes smart when the load bearing part also called the substrate is composed of conventional structural material and is integrated with the distributed actuation/sensor maybe piezoelectric, shape memory alloys, electrostrictive materials, magnetostrictive materials etc. In the present work, a systematic modelling technique is proposed for static and dynamic analysis of beam coupled with piezoelectric sensors/actuators by using the finite element method if formulation. The sensor/actuator layer made of a piezoelectric/polymer called PZT/PVDF is considered
Integrationof Data Mining and Design of Experiment to Diagnosis Machine Efficiency
Full text linkThe study focused on three phase induction motor because it is playing a vital role in production development. The motor may get the problem in some parts may effect in the wholeefficiency. Biannually maintenance increases the life of the machine, but many companies, especially in the third nation, do the maintenance as soon as the machine gets fail. The studyapplied two strategies to diagnosis and improve the efficiency of the machine. Design of experiment conducted to extract the main effect and interactions between variables. Three variables current, voltage, and power factor applied to understand the main effect in the exploited power (P). Power factor recorded the most important factor impacts the exploited power. Then, data mining utilized with two algorithms; random forests and linear regression. These algorithms used to predict the power factor — six variables collected for data mining, current, power losses, voltage, apparent power, resistance, and exploited power. These variables used to predict the power factor. From both strategies, we found that there is a strong relationship between exploited power and power factor, and those variables have a positive impact on the efficiency of the machine. Also, power losses and current have a negative impact on the power factor. Voltage did not give significant important whether in the design of experiment or data mining. Therefore, power losses and current must be controlled to keep the efficiency, and this can be done by regular maintenance by professional workers
Structural Health Monitoring: A Review
Full text linkThe use of Structural Health Monitoring (SHM) is a key to achieve technological leaps in the design and operation of engineering structures. Composite materials incorporating SHM systems enable the design and manufacture of tailored smart structures. This paper focuses on the application of SHM for various components including those in the maritime, oil and gas, civil infrastructure and other industries as a means of highlighting the issues that is faced by conventional methods. Incorporation of SHM has the potential to reduce through-life costs by the adoption of Condition Based Maintenance and to reduce operating costs by the design of more structurally efficient aircraft. The paper addresses the convenience involved in the design, certification, manufacture and through life support of such structures. Critical areas of development have been identified to enable the implementation of SHM in future composite structures
Portable Fuel Adulteration Detection System
Full text linkIn this paper a portable solution to the problem of adulteration in diesel is proposed. Techniques for checking adulteration in fuel are common. But, the biggest disadvantage of these is that these are lab based and hence require sophisticated testing and analysis in laboratories. The method that is proposed in this paper a portable apparatus that can be directly fitted in vehicles and adulteration can be checked on the go. The method employed uses polarimetry as the basis for sensing adulteration. The apparatus was designed after careful deliberation on various techniques that could be used for checking adulteration in diesel by kerosene. The proposed apparatus uses optical properties of the fuel samples to give the results
Delhi Air Pollution – A Review
No full textAir pollution is responsible for many health problems in the urban areas. Of late, the air pollution status in Delhi has undergone many changes in terms of the levels of pollutants and the control measures taken to reduce them. This paper provides an evidence-based insight into the status of air pollution in Delhi and its effects on health and control measures instituted. Delhi has taken several steps to reduce the level of air pollution in the city during the last few years. However, more still needs to be done to further reduce the levels of air pollution