Sudhish N. George

Sruthy. S, S. Yamuna, Sudhish N. George

Internet of Things (IoT) has emerged with a motive to automate the human life. It can be visualized as a network of connected things which is capable of providing intelligent services. This paper presents an IoT based security surveillance system in buildings using Raspberry Pi Single Board Computer (SBC) and NodeMCU (WiFi/IoT module). This system comprises of wireless sensor nodes and a controller section for surveillance. Intrusion detection with face detection and recognition, fire detection, remote user alerts, live video streaming and portability are the prime features of the system. The use of face recognition feature in intrusion detection makes the system more efficient by identifying the known and unknown person in restricted areas. WiFi module processes the sensor based events and sends the sensor status to controller section. Upon receiving the event notification, the controller enables the camera for capturing the event, alerts the user via email, phone call and Short Message Service (SMS) and places the live video of event on webpage. The use of WiFi module makes the node compact, cost effective and easy to use. The biggest advantage of the system is that the user can seek surveillance from anywhere in the world and can respond according to the situations.

Baburaj M., Sudhish N. George

This paper focus on recovering multi-dimensional data called tensor from randomly corrupted incomplete observation. Inspired by reweighted $l_1$ norm minimization for sparsity enhancement, this paper proposes a reweighted singular value enhancement scheme to improve tensor low tubular rank in the tensor completion process. An efficient iterative decomposition scheme based on t-SVD is proposed which improves low-rank signal recovery significantly. The effectiveness of the proposed method is established by applying to video completion problem, and experimental results reveal that the algorithm outperforms its counterparts.

M. Baburaj, Sudhish N. George

The t-SVD based Tensor Robust Principal Component Analysis (TRPCA) decomposes low rank multi-linear signal corrupted by gross errors into low multi-rank and sparse component by simultaneously minimizing tensor nuclear norm and l 1 norm. But if the multi-rank of the signal is considerably large and/or large amount of noise is present, the performance of TRPCA deteriorates. To overcome this problem, this paper proposes a new efficient iterative reweighted tensor decomposition scheme based on t-SVD which significantly improves tensor multi-rank in TRPCA. Further, the sparse component of the tensor is also recovered by reweighted l 1 norm which enhances the accuracy of decomposition. The effectiveness of the proposed method is established by applying it to the video denoising problem and the experimental results reveal that the proposed algorithm outperforms its counterparts.