3 research outputs found
Hybrid features for detection of malicious user in YouTube
Get PDFSocial media is any site that provides a network of people with a place to make connections. An example of the media is YouTube that connects people through video sharing. Unfortunately, due to the explosive number of users and various content sharing, there exist malicious users who aim to self-promote their videos or broadcast viruses and malware. Even though detection of malicious users have been done using various features such as
the content, user social activity, social network analyses, or hybrid features, the detection rate is still considered low (i.e., 46%). This study proposes a new set of features that includes features of the user, user behaviour and also features created based on Edge Rank concept. The work was realized by analysing a set of YouTube users and their shared video. It was followed by the process of classifying users using 22 classifiers based on the proposed feature set. An evaluation was performed by comparing the classification results of the proposed hybrid features against the non-hybrid ones. The undertaken experiments showed that most of the classifiers obtained better result when using the hybrid features as compared to using the non-hybrid set. The average classification accuracy is at 95.6% for the hybrid feature set. The result indicates that the proposed work would benefit YouTube users as malicious users who are sharing non-relevant content can be detected. The results
also lead to the optimization of system resources and the creation of trust among users
Detecting video spammers in YouTube social media
Get PDFSocial media is any site that provides a network of people with a place to make connections.An example of the media is YouTube that connects people through video sharing.Unfortunately, due to the explosive number of users and various content sharing, there exist malicious users who aim to self-promote their videos or broadcast unrelated content. Even though the detection of malicious users is based on various features such as content details, social activity, social network analyzing, or hybrid, the detection rate is still considered low (i.e. 46%).This study proposes a new set of features by constructing features based on the Edge Rank algorithm.Experiments were performed using nine classifiers of different learning; decision tree, function-based and Bayesian. The results showed that the proposed
video spammers detection feature set is beneficial as the highest accuracy (i.e average) is as high as 98% and the lowest was 74%.The proposed work
would benefit YouTube users as malicious users who are sharing non relevant content can be automatically detected.This is because system resources can be optimized as YouTube users are presented with the required
content only
Modern GPS diagnostic technique to determine and map soil hardpan for enhancing agricultural operation management
Get PDFAmong the undesirable effects of soil compaction is a measurable reduction in plant growth and crop yield. The prevailing belief is that compacted tillage pans are caused by repetitive farming practices, heavy tractors, tillage tools, and field traffic. This experiment was conducted to determine and map the hardpan layers across an agricultural field through advanced technologies of precision agriculture. These valuable techniques such as data logger, yield map, and data analysis of performance indicators were linked with accurate global positioning systems (GPS) datasets. These important technologies provided the farmers and helped them to identify and manage areas of the fields with higher compacted layers. Three ground speeds 4.3, 5.2, and 6.4 km h-1 were performed with two tillage depths 25 and 40 cm of a chisel plow. The effects of these two factors were studied to determine slippage percentage, field productivity, traction power, and fuel consumption. For the first shallow 25 cm depth, the results showed that increasing the speed from 4.3 to 5.2 and then to 6.4 km h-1 led to a significant increase in slippage percentage from 7.22 to 10.35 and then to 12.63%, respectively. Increasing the speed increases field productivity from 0.547 to 0.663 then to 0. 749 ha hour-1, and tractive power increases from 9.44 to 11.74, then to 13.24 hp. As a result, there was a significant increase in the fuel consumption rate from 18.44 to 20.15, then to 22.27 L hour-1, respectively. Changing the depth from 25 to 40 cm and increasing the practical speed from 4.3 to 5.2 and then to 6.4 km h-1 led to a significant increase in slippage percentage from 10.14 to 12.77 and then to 15.27%, and a significant increase in field productivity from 0.446 to 0.568 and then to 0.640 ha hour-1, respectively. This led to a significant increase in traction power from 12.72 to 13.36, then to 15.87 hp. Increasing the speed also brought a significant increase in fuel rate from 22.14 to 23.54 and then to 26.14 L ha-1, respectively. Based on this study, it was concluded that the use of this powerful approach was a useful methodology to reflect, determine, specify, and manage the regions of induced and hardpan zones by means of dataset analyses provided by the GPS for the desired field
