Activities of Daily Livings (ADLs) refer to the activities that are carried out by an individual for everyday living. Recognition of ADLs is key element for building intelligent and pervasive environments. We propose a two-layer HMM to build a ADLs recognition model that can represent the mapping between low-level sensor data and high-level activity based on the binary sensor data. We used embedded sensor with appliances or object to get object used sequence data as well as object name, type, interaction time, and location. In the first layer, we use location data of object used sensor to predict the activity class and in the second layer object used sequence data to determine the exact activity. We perform comparison with other activity recognition models using three real datasets to validate the proposed model. The results show that the proposed model achieves significantly better recognition performance than other models.
Human activity recognition has become an important research topic within the field of pervasive computing, ambient assistive living (AAL), robotics, health-care monitoring, and many more. Techniques for recognizing simple and single activities are typical for now, but recognizing complex activities such as concurrent and interleaving activity is still a major challenging issue. In this paper, we propose a two-phase hybrid deep machine learning approach using bi-directional Long-Short Term Memory (BiLSTM) and Skip-Chain Conditional random field (SCCRF) to recognize the complex activity. BiLSTM is a sequential generative deep learning inherited from Recurrent Neural Network (RNN). SCCRFs is a distinctive feature of conditional random field (CRF) that can represent long term dependencies. In the first phase of the proposed approach, we recognized the concurrent activities using the BiLSTM technique, and in the second phase, SCCRF identifies the interleaved activity. Accuracy of the proposed framework against the counterpart state-of-art methods using the publicly available datasets in a smart home environment is analyzed. Our experiment’s result surpasses the previously proposed approaches with an average accuracy of more than 93%.
of the experiment for both environments A and B; thus, the effectiveness of the simulation is confirmed. CONCLUSIONIndoor propagation has been measured at 30 points in the experimental room (4.525 ϫ 6.220 ϫ 2.700 m) in order to investigate the effectiveness of using an EM-wave absorber to improve a wireless LAN communications environment.A well-reflected environment, where the ceiling and the wall are metal and the floor is concrete, has been compared with one in which one long side wall is replaced by a three-layer absorber consisting of general building materials. The average absorption performance was found to be 10.4 dB (2.4 -2.5 GHz), which makes the average delay spread one-half of that of the well-reflected environment; further replacement of the ceiling with the sound-absorbing rock wool makes the spread equal to one-quarter.Simulation using the ray-tracing method was also performed in this room and the results for number of positions to the normalized delay spread calculated by the simulation are similar to those obtained from the experiment.Useful and necessary extensions of this work for other materials and under different conditions will be presented in future works. Printed array antennas are commonly used for microwave and millimeter-wave applications due to their attractive features such as low profile, ease of integration with other circuits, and conformability to planar or nonplanar surfaces as compared to parabolic reflectors. However, large printed array antennas have severe efficiency limitations at high frequencies (Ku or Ka bands) due to ohmic and dielectric losses, and parasitic radiations in long and complicated feed networks are dominantly increased [1]. Table 1 shows the calculated gain and directivity of the microstrip array and the gain of a dish at 10 GHz [1]. The microstrip array has a dielectric constant of 2.2, thickness of 1.6 mm, and spacing between elements of 0.8 0 ( 0 , is the free-space wavelength). A dish antenna has the same area as the microstrip array and an aperture efficiency of 50%. To overcome the drawbacks of the printed arrays, several high-gain printed arrays are studied [2][3][4]. It is also noticed that larger printed arrays are not practical when reasonable efficiency is required. In this work, a slot-array antenna using waveguide-fed subarrays backed by a single rectangular cavity is made and its characteristics are measured. Slot arrays are the most widely used antennas because they are relatively simple to build and analyze, and can be used for compact antenna systems [5][6][7]. An open slot antenna is free to radiate on both sides. A slot antenna can radiate into one side or have a unidirectional beam by using a cavity.Therefore, a cavity-backed slot antenna is of major interest in phased arrays, satellite-communication systems, and direct-broadcast satellite applications because of its compact size and high efficiency. In arrays containing a large number of elements, it may be impractical to back each slot with its individual cavity.In this study, groups of...
A new structure of an NFC loop antenna for mobile handset applications is proposed. The proposed antenna consists of conventional loop elements and a parasitic loop embedded capacitor to enhance its performance. Although the sintered ferrite sheets with higher relative permeability(μr≈200)have been used to reduce the performance deterioration due to the eddy current on the battery pack of a mobile handset, their costs are high, and they are considerably breakable. In this paper, with the proposed structure, we effectively enhance the performance of an NFC loop antenna by employing the ferrite-polymer composite with lower relative permeability(μr≈55).
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.