A Security Model for Big Data Usage on Cloud Computing (SMBDCC)
Maseeh Ullah Khan1 , Abdul Wahid Khan2
Abstract For the rapid growth of big data, cloud computing is a well-known approach for organization to improve the accessibility, management and processing of data on internet; but still cloud computing is not free from various security challenges. The main objective of our research is to develop a security model for Big Data usage on Cloud Computing (SMBDCC) that will assist software vendor organization to know in advance about security challenges and their practices for using big data on cloud computing. It will assist software vendor organization to know about their status while using big data on platform of cloud computing. For the data collection of our proposed research we will use systematic literature review (SLR). Then for the verification of these SLR results, pairwise comparison and prioritization of all challenges and practices we will use questionnaire survey, Analytical Hierarchy Process (AHP) respectively, and finally the developed model would be validated by industry specialists with the help of case study. The main purpose of our proposed model is the unique contribution to support software vendor organization about security related challenges of big data usage on cloud computing
Intelligence based Hepatitis Diagnosis: An Empirical Study
Muhammad Shahroz Gul Qureshi, Bilal Khan, Noor Muhammad Khan
Abstract: Liver disease is increasing on daily basis due to effect of drugs, viruses, alcohol and inherited diseases. Millions of people specially the young people’s fall in death due to liver diseases. Hepatitis is the kind of liver disease which effect the population of all age of groups. For early diagnosis of these diseases, a blood test is required once a year. Besides clinic tests, machine learning and pattern recognition methods have been widely used for early diagnosis of hepatitis diseases in medicine by specialists. The major issue is that, which techniques is to be selected and why? Hence, this study presents the comparative analysis of different machine learning techniques for the early prediction of hepatitis. To evaluate these techniques MAE, RAE, Precision, and Accuracy measure are used. The overall result shows that QDA and NB perform well in reducing the error rate and increasing the accuracy.
Road Sign Boards Detection & Recognition with Distance Calculation Alert system
Raja Osama Ayaz, Sikander, Memoona Khalid Mian
Abstract: Road Traffic and over speeding is a major problem which is increasing day by day which causes accidents. It occurs due to the negligence of traffic rules and sign boards located on the roads and highways. There are some traffic rules that must be followed. The highest death rate is caused by road accidents each year in Pakistan. This paper proposed highway sign board detection and alert system for following traffic rules and for safety. This system works though image processing and computer vision techniques i.e. SURF algorithm using MATLAB which detects sign boards on roads having different properties like color, shape, size etc. but one more thing which the uniqueness of our system is ultrasonic sensors which are attached to the system for measurement distances that at on how much distance the sign board is located. This system tells us what the sign is saying in both English and Urdu Language what the driver should do through LCD and speaker.
Anwar Hussain*, Muhammad Haris*, Abid Badshah, Ahmad Ishaq, Waseem Afsar
Abstract In this paper we proposed a classification algorithm, that use two methods of machine learning called Singular Value of Decomposition that is basically dimensionality reduction method, that takes useful information/features from dataset (images) and the second is Linear Discriminant Analysis (LDA) is a method used in image processing, pattern recognition and machine learning to find a linear combination of features that characterize or separates two or more classes of objects or events. In addition, we apply this algorithm on large image dataset and further use for gender classification problem. For example, face recognition and classification between male and female will be applied
