![]() Existing Spam filters have not been able to stop the SMS Spam problem due to frequent drift in spammer’s words, limited bag of words for training, device portability, and high computational overhead of filters. SMS Spam, which is an unsolicited or unwanted message, is a major problem with Global System for Mobile Communication (GSM) subscribers. It will also enable the clients to have a broad idea of the risks involved in his decision to move to the cloud and consequently takes care of them. The study will guide cloud consumers to conduct sufficient investigation in order to make a right choice of cloud provider. The study is based on industry knowledge and benchmarking, one of the security control proposed to resolving the insufficient due diligence threat. The focus of this study is to review literatures and extract those issues that consumers need to consider before moving into cloud. Consequently, many cloud users has committed themselves to cloud contracts on terms unfavourable to them exposing them to possible legal risk including breach of legal or regulatory obligations which may subject them to civil or even criminal liability due to lack of sufficient due diligence. Researchers show that the adoption of cloud-based services is now widespread. However, the risk and potential costs are also very real. Cloud computing is a new technology that promises a range of real benefits that include the ability to shift cost from capital to operational expenses, lower overall cost, greater agility and standardization, the ability to shift IT resources to higher-value-added activities, improve employee satisfaction and competitive advantage. Insufficient due diligence is the eighth of the top threats to the cloud technology as released by Cloud Security Alliance (CSA) in 2013. Future studies will target an enhanced AFLPRS with presence of smaller noisy characters, colour variations, extreme weather and uncontrolled illumination scenarios. True Positive (TP), True Negative (TN), False Negative (FN), False Positive (FP) and overall face recognition accuracy of AFLPRS on exit was 587, 16, 8, 7 and 97.6%, respectively. While AFLPRS face recognition performance on entry was SD=608 and 586 ED=10 and 37 CR=600 and 561, for side and middle deployment, respectively. SD and CR for overall LP characters was 96.26% and 19.74%, respectively. When deployed from the (side) and (middle) of the road, AFLPRS average Successful Detection (SD), Failure-to-detect (FTD) and Correct Recognition (CR) for LP characters was 512, 47, 115 and 594, 24, 127, AFLPRS was tested at FUNAAB main gate for 5 working days and the results obtained shows that 9176Ĭharacters were detected from 618 LPs during testing. AFLPRS combined licence plate recognition and facial recognition to track the car and the driver at the entry and exit point of the University premises. In this study, an automatic facial and licence plate recognition system (AFLPRS) was designed and developed. Licence plates (LP) recognition has been applied in car access control, toll collection and other applications in recent times. We can reduce the number of word attributes by almost 50% without reducing accuracy significantly, using our usability-based approach. ![]() Thus, we conclude that filtering SMS spam can be performed on independent mobile phones. Our experiment on an Android mobile phone shows that it can filter SMS spam with reasonable accuracy, minimum storage consumption, and acceptable processing time without support from a computer or using a large amount of SMS data for training. As such, we apply a probabilistic Naïve Bayes classifier using word occurrences for screening because of its simplicity and fast performance. The mobile phone has storage, memory and CPU limitations compared with a computer. The training, filtering, and updating processes are performed on an independent mobile phone. Thus, we propose to filter SMS spam on independent mobile phones using Text Classification techniques. This increases hardware maintenance and communication costs. However, they require a computer or a large amount of SMS data in advance to filter SMS spam, especially for the training. Most of these use Text Classification techniques that consist of training, filtering, and updating processes. Various solutions to filter SMS spam on mobile phones have been proposed. ![]() The amount of Short Message Service (SMS) spam is increasing.
0 Comments
Leave a Reply. |