Online ISSN: 2515-8260

Author : GALAV, RAKESH KUMAR


Detection and Identification of Bogus Profiles in online Social Network using Machine Learning Methods

ANANT RAM; RAKESH KUMAR GALAV

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 395-400

Here current creation online social networks (OSNs) become more and more common and the social life of people has become more linked to these pages. They use OSNs to remain in finger with everyone else, distribute news, prepare dealings and still run their personal e-. Out of control of the OSN's evolution and the huge extent of their supporters 'individual developments, they have been attackers and impostors who take individual information, share fake news and disseminate vindictive exercises. Researchers in various fields began inspecting environmentally friendly techniques in order to perform abnormal activity and counterfeit money that is based on accounting and classification algorithms [1]. However, the use of stand-alone classification algorithms no longer yields a straightforward outcome, some of the factors that are manipulated by the account have a low influence or have no impact in the closing results. The paper proposes to use the SVM-NN as a modern algorithm to effectively identify suspected Twitter accounts and bots, to add four choices and to restrict measurements. Three laptop classification mastering algorithms were used to determine the actual or false identity of target accounts. They included the SVM, the Neural Network and our recently urbanized SVM-NN method that utilizes far less hardware but is still able to correctly identify about 98% of the money due to the training data set.

Identification of Speech Signal in Moving Objects using Artificial Neural Network System

DIWAKAR BHARDWAJ; RAKESH KUMAR GALAV

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 418-424

The speech signal moving objects regarding the speaker’s personality. A speaker recognition field is about retrieving the name of the individual voicing the speech. The effectiveness of accurately identifying a speaker is focused solely on vocal features, as voice contact with machines is becoming more prevalent in tasks like telephone, banking transactions, and the transformation of data from speech databases. This review illustrates the detection of text-dependent speakers, which identifies a single speaker from a known population. The program asks the user to utter voice. Program recognizes the person through evaluating the voice utterance codebook with the voice utterance codebook held in the database and records that may have provided the voice speech. Furthermore, the features are removed; the speech signal is registered for 6 speakers. Extraction of the function is achieved using LPC coefficients, AMDF calculation and DFT. By adding certain features as input data, the neural network is equipped. For further comparison the characteristics are stored in models. The characteristics that need to be defined for the speakers were obtained and analyzed using Back Propagation Algorithm to a template image. Now this framework trained correlates to the outcome; the source is the characteristics retrieved from the speaker to be described. The weight adjustment is done by the system, and the similarity score is discovered to recognize the speaker. The number of iterations needed for achieving the goal determines the efficiency of the network.