<span>Nowadays data mining become one of the technologies that paly major effect on business intelligence. However, to be able to use the data mining outcome the user should go through many process such as classified data. Classification of data is processing data and organize them in specific categorize to be use in most effective and efficient use. In data mining one technique is not applicable to be applied to all the datasets. This paper showing the difference result of applying different techniques on the same data. This paper evaluates the performance of different classification techniques using different datasets. In this study four data classification techniques have chosen. They are as follow, BayesNet, NaiveBayes, Multilayer perceptron and J48. The selected data classification techniques performance tested under two parameters, the time taken to build the model of the dataset and the percentage of accuracy to classify the dataset in the correct classification. The experiments are carried out using Weka 3.8 software. The results in the paper demonstrate that the efficiency of Multilayer Perceptron classifier in overall the best accuracy performance to classify the instances, and NaiveBayes classifiers were the worst outcome of accuracy to classifying the instance for each dataset.</span>

No abstract

Vehicular Ad hoc Networks (VANET) is one of the emerging mobile ad hoc networking paradigms (MANET), where the self-organizing and infrastructure-less nature of MANET structure. In VANETs, vehicle nodes communicate with each other using wireless links. However, the nodes are highly mobile and the topology of the network changes rapidly. Therefore, the design of routing protocols in VANETs is still a crucial issue. In this paper, we examine two of the most recent routing protocols that proposed for MANETs to select the optimal path between source-destination pairs, namely: Dynamic MANET On-demand (DYMO) and Optimized Link State Routing version 2 (OLSRv2) routing protocols. We evaluated and compared the performance of both protocols based on different parameters under various simulation scenarios. The result has shown that the DYMO protocol has higher through put and packet delivery ratio compare to the OLSRv2 protocol. However, the OLSRv2 protocols has better performance in the terms of average jitter and end to end delay compare to the DYMO protocol based on the paper's scenario. OLSRv2 should be selected if the system concerns about time delay and jitter, otherwise it should be selected DYMO to achieve higher throughput and high packet delivery.

The key indication of a nation's economic development and strength is the stock market. Inflation and economic expansion affect the volatility of the stock market. Given the multitude of factors, predicting stock prices is intrinsically challenging. Predicting the movement of stock price indexes is a difficult component of predicting financial time series. Accurately predicting the price movement of stocks can result in financial advantages for investors. Due to the complexity of stock market data, it is extremely challenging to create accurate forecasting models. Using machine learning and other algorithms to anticipate stock prices is an interesting area. The purpose of this article is to forecast stock market values to assist investors to make better informed and precise investing decisions. Statistics, Machine Learning (ML), Natural language processing (NLP), and sentiment analysis will be used to accomplish the study's objectives. Using both qualitative and quantitative information, the study developed a hybrid model. The hybrid model has been handled with GANs. Based on the model's predictions, a buy-or-sell trading strategy is offered. The conclusions of this study will assist investors in selecting the ideal choice while selling, holding, or buying shares.

Online advertising is a growing business. Owing to the advances in Internet technology, the nature and types of advertisements (hereinafter, "ads") have changed. Many companies use different types of advertising to reach their customers. This paper shows how Internet users perceive online advertising. The findings are meant to help companies and institutions develop effective ads that appeal to consumers. Moreover, the study proposes an extended model for the main variables that affect customers' attitudes toward online advertising. The four variables are credibility, entertainment, informativeness, and irritation. The study was conducted on a sample of Turkish university students. The data were collected via a survey that was administered to participants, and 602 valid responses were used for data analysis. The data were analyzed using SPSS and SmartPLS 3 software. Results revealed that the four hypotheses were supported. Specifically, most users find that the listed types of ads disturb them. Online advertising was negatively perceived by study participants. Through the outcome of this study, the governmental sectors can monitor advertisements, ensure the welfare of users, legislate laws according to what meets the government's needs and policies. In addition, the study will help companies and institutions to increase the opportunities to accept their advertisements by consumers.