Face recognition system is broadly used for human identification because of its capacity to measure the facial points and recognize the identity in an unobtrusive way. The application of face recognition systems can be applied to surveillance at home, workplaces, and campuses, accordingly. The problem with existing face recognition systems is that they either rely on the facial key points and landmarks or the face embeddings from FaceNet for the recognition process. In this paper, we propose a hierarchical network (HN) framework which uses pre-trained architecture for recognizing faces followed by the validation from face embeddings using FaceNet. We also designed a real-time face recognition security door lock system connected with raspberry pi as an implication of the proposed method. The evaluation of the proposed work has been conducted on the dataset collected from 12 students from Faculty of Engineering and Technology, University of Sindh. The experimental results show that the proposed method achieves better results over existing works. We also carried out a comparison on random faces acquired from the Internet to perform face recognition and results shows that the proposed HN framework is resilient to the randomly acquired faces.
19 November 2016 in Wireless Personal Communications
Since the last decade, the number of Internet of Things (IoT) devices has increased dramatically and to operate them at low power has been a great challenge. Therefore, significant efforts have been made by the researchers to innovate such technologies that may operate the IoT devices at low power. In this context, several Low Power Wide Area Network (LPWAN) technologies have been introduced which have revolutionized the world of IoT. Narrowband Internet of Things (NB-IoT) is one of the protocols that was developed by 3rd Generation Partnership Project (3GPP) in June 2016 to cater the stringent requirements of IoT devices. In this paper, a comprehensive analysis on the features, architecture, signals and channels of NB-IoT is provided. Additionally, a detailed description of the applications of NB-IoT is also presented. Finally, some crucial challenges related to the quality of service (QoS) of NB-IoT are highlighted in this paper.
This paper evaluates the feasibility of Radio-over-Plastic Optical Fiber (RoPOF) technology for LTE and Internet of Things (IoT) service providing in future short-range communication networks. In particular, we have focused on the downlink transmission of 10-MHz LTE and Narrow-Band IoT (NB-IoT) in guardband operation mode over a carrier frequency of 800 MHz. By selecting the proper components and transmission parameters, the impact of the input power and the relative power of NB-IoT to LTE over the Error Vector Magnitude (EVM) has been experimentally analyzed for both signals. For this purpose, a RoPOF communication link using a 75-meter Graded-index POF (GI-POF) has been established, while the main signal processing tasks as modulation/ demodulation and EVM estimation are performed offline. Results show that transmission performance meets the standard quality for both signals using a wide range of input powers. Additionally, the use of the LTE guardband for NB-IoT transmission hardly affects its quality indicating the strength of this spectrally-efficient solution.