In Wireless Body Area Networks (WBANs), the extremely sensitive data transmission mainly requires fault tolerance and consistent data transmission. In this study, we propose a Cluster Based Failure Detection and Recovery Technique for WBAN which presents a hierarchical architecture. Here, local nodes are connected to their Cluster Heads (CHs). Each CH is interconnected and also connected with a Wireless Local Gateway (WLG). Finally, WLG is connected to Hospital Gateway (HG). Each local sensor collects the fault related information and each node is assigned with priority to measure the fault tolerant level of individual nodes. Nodes with high priority are processed first. Further, node and CH level faulty node detection and recovery schemes are also proposed. Our technique provides both reliability and fault tolerance. The efficiency of our technique is proved through simulation results.

In IEEE 802.15.4 Body Area Networks (BAN), security solution is required for data confidentiality, authentication and integrity at low cost. But the existing solutions for WBAN either provide any one of the security features or provide all the features with high cost. In this paper, we propose to develop light-weight security architecture for IEEE 802.15.4 BAN. It consists of local sensors situated on various parts of the body which forms various clusters. The local sensor collects data from different parts of the body and transmits the data to their respective cluster head. A wireless local gateway (WLG) is deployed within the patient's home and a hospital gateway (HG) is set in the hospital. The cluster head transmits the data securely to the WLG. At WLG, a new message is created by aggregating all messages from various clusters of a patient. A secret key is generated using Elliptic Curve Cryptography (ECC) for encryption and the encrypted message with message authentication code (MAC) is transmitted to the HG. At the destination, the doctor first authenticates the MAC and then decrypts the data with the secret key and monitors the patient's health condition. Thus the data cannot be read by any other person, providing a secured transmission at low cost.

Prediction of student performance at early stage in higher education is important for academic society so that strategic decisions can be made before students are placed to keep them from dropping out of the course. Due to India's massive student population and extremely ancient educational system, there are significant difficulties in measuring and forecasting students' performance. Every institution in India has its own unique set of criteria for measuring student achievement, and there is no formal process for keeping track of and evaluating a student's progress and improvement. Over the last decade, researchers in the education domain have presented numerous types of machine learning techniques. However, there are significant obstacles to dealing with imbalanced datasets in order to predict the performance of students. In this paper, the first phase of traditional classification algorithms has been applied to the dataset, which contains the progress of 4424 students. In the second phase, novel hybrid machine learning (ML) algorithms were used to get better predictions. The outcome of the proposed model makes it easier to predict how well students will do so that early decisions can be made about the growth of higher education institutions.

Peer-to-Peer Video-on-Demand (VoD) is a capable solution which offers thousands of videos to millions of users with complete interactive watching. Most of the commercial P2P streaming deployments PPLive, PPStream, UUSee have introduced a multi-channel P2P VoD system that allows user to view more than one channel at a time. Recent research studies have proposed a cross channel resource sharing algorithms to utilize the individual peer resources effectively, including bandwidth and cache capacity by enabling crosschannel cooperation among multiple channels. However, current multiple channel P2P VoD system deliver a video at a low streaming rate due to the channel resource imbalance and channel churn. In order to improve the streaming capacity, this paper proposes different effective helpers based resource balancing scheme that actively identifies the supply-anddemand imbalance in multiple channels. Furthermore, peers in a surplus channel serve its unused bandwidth resources to peers in a deficit channel that minimizes the server bandwidth consumption. This approach proposes a tracker assisted peer scheduling policy that effectively schedules the different chunks within each video in the process of fetching and serving chunks without impairing the streaming quality. Experimental evaluation shows that the proposed tracker assisted scheduling strategy achieves high streaming capacity under reduced server workload and improves streaming quality when compared to existing algorithms.