International Journal of Computer Science and Engineering

1-8

Authors: Ahmed Sami Jaddoa & Ziyad Tariq Mustafa Al-Ta'i

Diabetes is specified as the most chronic and deadliest disease that results in increasing blood sugar. The medical data mining approaches were utilized for detectingun observed patterns in the medical field sof sets of data for medical diagnosis and treatment. Data classification for diabetes mellitus is quite significant. Where utilizing two types of data sets, the first is local, collected from consulting laboratories at Baqubah General Hospital, and the second is global, which is the Pima India Diabetes Database. The experiment on the Local dataset shows that the accuracy if K-NN is 90 %, the accuracy of the SVM has been 98 %, the accuracy of the NB is 98 % and the accuracy of RF is 98 %. The experiment on the Pima dataset shows that the accuracy of K-NN is 81 %, the accuracy of SVM has been82 %, the accuracy of NB is 84 % and the accuracy of RF is 82 %.

17-26

Authors: Pranavi Patel & Mala Mehta

With the growing usage in the field of IoT (Internet of Things), yber threats and malicious activities are also at their peak. Widening in the utilization of the Internet of Things (IoT) as raised awareness of security and has become a major concern of many IoT users. For the smooth working of IoT networks, it is essential to protect devices from malicious activities. For security purposes, an advanced Intrusion Detection System (IDS)is required. In this paper, we discussed approaches of IDS and different datasets. Later on, IDS types on the basis of application are discussed with their limitations. For future assessment, current challenges faced by IDS of IoT are discussed. An ID plays a pivotal role in IoT by discovering and repealing malicious activity for lag-free service networks.