Human activity recognition from sensor data is a fundamental research topic to achieve remote health monitoring and ambient assisted living (AAL). In AAL, sensors are integrated into conventional objects aimed at enabling people's capabilities through digital environments that are sensitive, responsive and adaptive to human activities. Moreover, new technological approaches to support AAL within the home or community setting offers people the prospect of more individually focused care and improved quality of living. In the present work, an ambient human activity classification framework that augments information from the received signal strength indicator (RSSI) of passive RFID tags to obtain detailed activity profiling is proposed. Key indices of position, orientation, mobility, and degree of activities which are critical to guide reliable clinical management decisions using 4 volunteers are employed to simulate the research objective. A twolayer, fully connected sequence long short-term memory recurrent neural network model (LSTM RNN) is implemented. The LSTM RNN model extracts the feature of RSS from the sensor data and classifies the sampled activities using SoftMax. The performance of the LSTM model is evaluated for different data size and the hyper-parameters of the RNN are adjusted to optimal states, which results in an accuracy of 98.18%. The proposed framework suits well for smart homes and smart health and offers a pervasive sensing environment for the elderly, persons with disability and chronic illness.
Reconfigurable radiation pattern shaping by means of circular disc planer antenna with a slot ring is presented. The proposed microstrip antenna has an overall dimension of 70×70mm 2 designed on a substrate of a dielectric constant 4.3. The designed antenna operates at 5.35 GHz with a central coaxial probe feed. By altering the configuration of two PIN diodes switches, the designed antenna has three different beam patterns in the yz plane. Biasing each diode separately result in about 60 o change in the main radiation pattern steering angle, while the frequency response are largely maintained. At resonance, the peak gains are approximately 3.5 dB, 4 dB and 4.3 dB, in the three configurations of the diodes. Return losses, peak gains and reconfigurable radiation patterns are reported, which are in very good agreement for WiMax/WiFi (IEEE 802.11a) applications.
In this paper, a new design of multiple-input/multiple-output (MIMO) antenna is proposed for 3.6 GHz fifth generation (5G) mobile communications. The proposed design contains four pairs of compact microstrip-fed dual-polarized antennas that are symmetrically placed at the four corners of the smartphone printed circuit board (PCB). Each antenna pair consists of a square loop radiation patch and a square defected ground structure (DGS). The loop radiators are fed by two independently coupled Tshaped microstrip feeding lines, which can exhibit radiation pattern and polarization diversity. Therefore, the proposed 5G smartphone antenna design contains four horizontally polarized and four vertically-polarized antennas in total. A low-cost FR-4 dielectric (ε= 4.4, δ= 0.02) with a dimension of 75×150 mm 2 is used as the PCB substrate. The characteristics of the smartphone antenna are examined using both simulations and measurements. It offers good isolation, dual-polarized full radiation coverage, and sufficient efficiency. In addition, the calculated envelope correlation coefficient (ECC) and total active reflection coefficient (TARC) of the design are very low over the entire operation band.
A modified indoor path loss prediction model is presented, namely, effective wall loss model. The modified model is compared to other indoor path loss prediction models using simulation data and real‐time measurements. Different operating frequencies and antenna polarizations are considered to verify the observations. In the simulation part, effective wall loss model shows the best performance among other models as it outperforms 2 times the dual‐slope model, which is the second best performance. Similar observations were recorded from the experimental results. Linear attenuation and one‐slope models have similar behavior, the two models parameters show dependency on operating frequency and antenna polarization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.