The smartphone-based human activity recognition (HAR) systems are not capable to deliver high-end performance for challenging applications. We propose a dedicated hardware-based HAR system for smart military wearables, which uses a multilayer perceptron (MLP) algorithm to perform activity classification. To achieve the flexible and efficient hardware design, the inherent MLP architecture with parallel computation is implemented on FPGA. The system performance has been evaluated using the UCI human activity dataset with 7767 feature samples of 20 subjects. The three combinations of a dataset are trained, validated, and tested on ten different MLP models with distinct topologies. The MLP design with the 7-6-5 topology is finalized from the classification accuracy and cross entropy performance. The five versions of the final MLP design (7-6-5) with different data precision are implemented on FPGA. The analysis shows that the MLP designed with 16-bit fixed-point data precision is the most efficient MLP implementation in the context of classification accuracy, resource utilization, and power consumption. The proposed MLP design requires only 270 ns for classification and consumes 120 mW of power. The recognition accuracy and hardware results performance achieved are better than many of the recently reported works. INDEX TERMS Human activity recognition, multilayer perceptron, smart military wearables, classifier hardware implementation, field programmable gate array.

No abstract

No abstract

The crystal structure of the title compound, CtlHTBrO3, has been determined using 1549 observed reflections with I > 2.5o-(/). The coumarin moiety is planar and makes a dihedral angle of 6.6 (4) ° with the mean plane of the acetyl group attached to C(3). The molecules adopt the S-cis configuration in the crystal and are linked by weak CmH ..

An electroactive poly(3,4-(2,2-dimethylpropylenedioxy)thiophene) (PProDOT-Me 2 ) thin film was electropolymerized by cyclic voltammetry technique, and its electrochemical and electrochromic properties were systematically studied. The prepared PProDOT-Me 2 thin film was electrochemically reversible, and it showed a linear relation between peak current with scan rates. The electrochemical impedance spectrum also indicated the diffusion limitation of the film during charge/discharge process. The film showed a good color contrast (60 %) with a low applying potential of 1.2 V. The electrochromic window (ECW) based on PPro-DOT-Me 2 film was fabricated and studied for its electrochromic performance. The color contrast of the device was achieved as 36 % at k max of 560 nm. The switching speed of fabricated ECW for coloring and bleaching were almost 0.7 s in a range of ?1.5 to -1.5 V. The fabricated device showed better cyclic current response and remarkable switching stability over 100 cycles. The novelty of the electrochromic window based on PProDOT-Me 2 is the maximum absorbance at photopic wavelength that would be highly sensitive to human eyes.